Matching Process
07 diciembre, 2020
Model
library(DiagrammeR)
# Nodes
#node [shape = box]
# S [label = 'Matched\n(S=1)',fontsize=7]
# C [label = 'Not censored\n(C=0)',fontsize=7]
gr1<-
DiagrammeR::grViz("
digraph causal {
# Nodes
node [shape = plaintext]
a [label = 'Observed\nConfounders\n(Z)',fontsize=10]
b [label = 'Unobserved\nConfounders\n(U)',fontsize=10]
c [label = 'Early\nDrop-out\n(Y)',fontsize=10]
d [label = 'Residential\nPrograms\n(X)',fontsize=10]
# Edges
edge [color = black,
arrowhead = vee]
rankdir = TB;
b -> c
b -> a
a -> c
d -> c [minlen=1]
d -> a [minlen=1]
# a -> S #[minlen=1]
# Z -> S #[minlen=1]
# a -> C #[minlen=3]
# Z -> C #[minlen=3]
{ rank = same; b; a; c }
# { rank = same; S; C }
{ rankdir = LR; a; d }
# Graph
graph [overlap = true]
}")
gr1Figure 1. Directed Acyclic Graph
# {rank=same ; A -> B -> C -> D};
# {rank=same ; F -> E[dir=back]};
#https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3733703/
#Cohort matching on a variable associated with both outcome and censoring
#Cohort matching on a confounder. We let A denote an exposure, Y denote an outcome, and C denote a confounder and matching variable. The variable S indicates whether an individual in the source population is selected for the matched study (1: selected, 0: not selected). See Section 2-7 for details.
#https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7064555/
gr2<-
DiagrammeR::grViz("
digraph causal {
# Nodes
node [shape = plaintext]
a [label = 'Residential\nPrograms\n(X)',fontsize=10]
b [label = 'Unobserved\nConfounders\n(U)',fontsize=10]
c [label = 'Early\nDrop-out\n(Y)',fontsize=10]
d [label = 'Observed\nConfounders\n(Z)',fontsize=10]
# Edges
edge [color = black,
arrowhead = vee]
rankdir = TB
a -> c [minlen=3]
d -> a [minlen=3]
d -> c [minlen=9]
b -> a [minlen=1]
b -> c
{ rank = same; c; d }
#{ rank = same; b; d }
rankdir = TB
{ rank = same; d; c } #Ver si lo saco, creo que da problemas
# Graph
graph [overlap = true]
}")#LRBalance
We selected treatments at baseline for each user, leaving 85,048 observations. Then, we distinguished between residential 12,706 and ambulatory (72,267) treatments. We imputed cases that did not have a defined treatment assigned 75.
We selected the following variables of interest:
- “Starting Substance” (
sus_ini_mvv) - “Marital Status” (
estado_conyugal_2) - “Educational Attainment” (
escolaridad_rec) - “Age of Onset of Drug Use” (
edad_ini_cons) - “Frequency of use of primary drug” (
freq_cons_sus_prin) - “Motive of Admission to Treatment” (
origen_ingreso_mod) - “Psychiatric co-morbidity” (
dg_cie_10_rec) - “Drug Dependence” (
dg_trs_cons_sus_or) - “Chilean Region of the Center” (
nombre_region) - “Type of Center (Public)” (
tipo_centro_pub) - “Sex” (
sexo_2) - “Age at Admission to Treatment” (
edad_al_ing) - “Date of Admission to Treatment” (
fech_ing_num) - “Evaluation of the Therapeutic Process” (*) (
evaluacindelprocesoteraputico) - “Early Dropout (Against Staff Advice)” (
abandono_temprano_rec) (Y) - “Residential Type of Plan” (
tipo_de_plan_res) (Z)
library(compareGroups)
match.on_tot <- c("row", "hash_key","sus_ini_mod_mvv","estado_conyugal_2","escolaridad_rec","edad_ini_cons","freq_cons_sus_prin","origen_ingreso_mod","dg_cie_10_rec","nombre_region","tipo_centro_pub","sexo_2","edad_al_ing","fech_ing_num","abandono_temprano_rec","tipo_de_plan_res","duplicates_filtered","dg_trs_cons_sus_or","evaluacindelprocesoteraputico")
#dg_trs_cons_sus_or
CONS_C1_df_dup_SEP_2020_match<-
CONS_C1_df_dup_SEP_2020 %>%
dplyr::filter(dup==1) %>% #, tipo_de_plan_2 %in% c("PG-PR","M-PR","PG-PAI","M-PAI","PG-PAB","M-PAB")
dplyr::mutate(tipo_de_plan_res=dplyr::case_when(grepl("PR",as.character(tipo_de_plan_2))~1,
grepl("PAI",as.character(tipo_de_plan_2))~0,
grepl("PAB",as.character(tipo_de_plan_2))~0,
TRUE~NA_real_)) %>%
dplyr::mutate(tipo_de_plan_res=factor(tipo_de_plan_res)) %>%
dplyr::mutate(abandono_temprano_rec=factor(if_else(as.character(motivodeegreso_mod_imp)=="Early Drop-out",TRUE,FALSE,NA))) %>%
dplyr::mutate(dg_trs_cons_sus_or=factor(if_else(as.character(dg_trs_cons_sus_or)=="Drug dependence",TRUE,FALSE,NA))) %>%
dplyr::mutate(tipo_centro_pub=factor(if_else(as.character(tipo_centro)=="Public",TRUE,FALSE,NA))) %>%
dplyr::mutate(condicion_ocupacional_corr=factor(condicion_ocupacional_corr),cat_ocupacional_corr=factor(cat_ocupacional_corr)) %>%
dplyr::mutate(dg_trs_fis_rec=factor(dplyr::case_when(as.character(diagnostico_trs_fisico)=="En estudio"~"Diagnosis unknown (under study)",as.character(diagnostico_trs_fisico)=="Sin trastorno"~'Without physical comorbidity',cnt_diagnostico_trs_fisico>0 ~'With physical comorbidity',
TRUE~NA_character_)))%>%
dplyr::mutate(escolaridad_rec=parse_factor(as.character(escolaridad_rec),levels=c('3-Completed primary school or less', '2-Completed high school or less', '1-More than high school'), ordered=T,trim_ws=T,include_na =F, locale=locale(encoding = "Latin1"))) %>%
dplyr::mutate(freq_cons_sus_prin=parse_factor(as.character(freq_cons_sus_prin),levels=c('Did not use', 'Less than 1 day a week','2 to 3 days a week','4 to 6 days a week','1 day a week or more','Daily'), ordered =T,trim_ws=T,include_na =F, locale=locale(encoding = "UTF-8"))) %>%
dplyr::mutate(evaluacindelprocesoteraputico=dplyr::case_when(grepl("1",as.character(evaluacindelprocesoteraputico))~'1-High Achievement',grepl("2",as.character(evaluacindelprocesoteraputico))~'2-Medium Achievement',grepl("3",as.character(evaluacindelprocesoteraputico))~'3-Minimum Achievement', TRUE~as.character(evaluacindelprocesoteraputico))) %>%
dplyr::mutate(evaluacindelprocesoteraputico=parse_factor(as.character(evaluacindelprocesoteraputico),levels=c('1-High Achievement', '2-Medium Achievement','3-Minimum Achievement'), ordered =T,trim_ws=T,include_na =F, locale=locale(encoding = "UTF-8"))) %>%
dplyr::select_(.dots = match.on_tot) %>%
dplyr::mutate(more_one_treat=factor(ifelse(duplicates_filtered>1,1,0))) %>%
data.table::data.table()## Warning: `select_()` is deprecated as of dplyr 0.7.0.
## Please use `select()` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_warnings()` to see where this warning was generated.#CONS_C1_df_dup_SEP_2020_match %>%
#dplyr::group_by(dg_trs_fis) %>% dplyr::summarise(q1=quantile(dias_treat_imp_sin_na,.25),q2=quantile(dias_treat_imp_sin_na,.5),q3=quantile(dias_treat_imp_sin_na,.75)) ---> las distribuciones por días de tratamiento de las categorías de respuesta tienden a ser bastante similares, aunquequienes tienen una comorbiliad física definida tienen más tiempo en el estudio.
invisible("La diferencia en días de tratamiento entre las categorías de enfermedad psiquiátrica, indica que quienes se encuentran en estudio tienen muchos menos días en tratamiento que quienes no tienen una comorbilidad o quienes tienen una definida. No es lo mismo con el caso de la enfermedad física, en donde tienden a ser bastante similares")
invisible("Decidí no incluir diagnóstico de enferemedad física, porque hay algunas condiciones que son crónicas o que pueden serlo, y que no tengo cómo validarlas a lo largo del tratamiento")
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
attr(CONS_C1_df_dup_SEP_2020_match$sus_ini_mod_mvv,"label")<-"Starting Substance"
attr(CONS_C1_df_dup_SEP_2020_match$estado_conyugal_2,"label")<-"Marital Status"
attr(CONS_C1_df_dup_SEP_2020_match$escolaridad_rec,"label")<-"Educational Attainment"
attr(CONS_C1_df_dup_SEP_2020_match$edad_ini_cons,"label")<-"Age of Onset of Drug Use"
attr(CONS_C1_df_dup_SEP_2020_match$freq_cons_sus_prin,"label")<-"Frequency of use of primary drug"
attr(CONS_C1_df_dup_SEP_2020_match$origen_ingreso_mod,"label")<-"Motive of Admission to Treatment"
attr(CONS_C1_df_dup_SEP_2020_match$dg_cie_10_rec,"label")<-"Psychiatric co-morbidity"
attr(CONS_C1_df_dup_SEP_2020_match$nombre_region,"label")<-"Chilean Region of the Center"
attr(CONS_C1_df_dup_SEP_2020_match$tipo_centro_pub,"label")<-"Type of Center (Public)"
attr(CONS_C1_df_dup_SEP_2020_match$sexo_2,"label")<-"Sex"
attr(CONS_C1_df_dup_SEP_2020_match$edad_al_ing,"label")<-"Age at Admission"
attr(CONS_C1_df_dup_SEP_2020_match$fech_ing_num,"label")<-"Date of Admission to Treatment"
attr(CONS_C1_df_dup_SEP_2020_match$abandono_temprano_rec,"label")<-"Early Dropout"
attr(CONS_C1_df_dup_SEP_2020_match$tipo_de_plan_res,"label")<-"Residential Type of Plan"
attr(CONS_C1_df_dup_SEP_2020_match$duplicates_filtered,"label")<-"No. of Treatments in the Database"
attr(CONS_C1_df_dup_SEP_2020_match$dg_trs_cons_sus_or,"label")<-"Drug Dependence"
attr(CONS_C1_df_dup_SEP_2020_match$evaluacindelprocesoteraputico,"label")<-"Evaluation of the Therapeutic Process"
knitr::opts_chunk$set(echo = FALSE, warning=FALSE, message=FALSE)
table1_all <- suppressWarnings(compareGroups(tipo_de_plan_res ~ sus_ini_mod_mvv+ estado_conyugal_2+ escolaridad_rec+ edad_ini_cons+ freq_cons_sus_prin+ origen_ingreso_mod+ dg_cie_10_rec+ nombre_region+ tipo_centro_pub+ sexo_2+ dg_trs_cons_sus_or+ edad_al_ing+ fech_ing_num+ abandono_temprano_rec+ duplicates_filtered+ dg_trs_cons_sus_or+ evaluacindelprocesoteraputico, method= c(
sus_ini_mod_mvv=3,
estado_conyugal_2=3,
escolaridad_rec=3,
edad_ini_cons=3,
freq_cons_sus_prin=3,
origen_ingreso_mod=3,
dg_cie_10_rec=3,
dg_trs_cons_sus_or=3,
nombre_region=3,
tipo_centro_pub=3,
sexo_2=3,
dg_trs_cons_sus_or=3,
edad_al_ing=2,
fech_ing_num=2,
abandono_temprano_rec=3,
duplicates_filtered=3,
evaluacindelprocesoteraputico=3),
data = CONS_C1_df_dup_SEP_2020_match,
include.miss = T,
var.equal=T)
)
table1_more_one <- suppressWarnings(compareGroups(tipo_de_plan_res ~ sus_ini_mod_mvv+ estado_conyugal_2+ escolaridad_rec+ edad_ini_cons+ freq_cons_sus_prin+ origen_ingreso_mod+ dg_cie_10_rec+ dg_trs_cons_sus_or+ nombre_region+ tipo_centro_pub+ sexo_2+ dg_trs_cons_sus_or+ edad_al_ing+ fech_ing_num+ abandono_temprano_rec+ evaluacindelprocesoteraputico, method= c(
sus_ini_mod_mvv=3,
estado_conyugal_2=3,
escolaridad_rec=3,
edad_ini_cons=3,
freq_cons_sus_prin=3,
origen_ingreso_mod=3,
dg_cie_10_rec=3,
dg_trs_cons_sus_or=3,
nombre_region=3,
tipo_centro_pub=3,
sexo_2=3,
dg_trs_cons_sus_or=3,
edad_al_ing=2,
fech_ing_num=2,
abandono_temprano_rec=3,
evaluacindelprocesoteraputico=3),
data = CONS_C1_df_dup_SEP_2020_match,
include.miss = T,
var.equal=T,
subset= more_one_treat==1)
)
table1_only_one <- suppressWarnings(compareGroups(tipo_de_plan_res ~ sus_ini_mod_mvv+ estado_conyugal_2+ escolaridad_rec+ edad_ini_cons+ freq_cons_sus_prin+ origen_ingreso_mod+ dg_cie_10_rec+ dg_trs_cons_sus_or+ nombre_region+ tipo_centro_pub+ sexo_2+ dg_trs_cons_sus_or+ edad_al_ing+ fech_ing_num+ abandono_temprano_rec+ evaluacindelprocesoteraputico, method= c(
sus_ini_mod_mvv=3,
estado_conyugal_2=3,
escolaridad_rec=3,
edad_ini_cons=3,
freq_cons_sus_prin=3,
origen_ingreso_mod=3,
dg_cie_10_rec=3,
dg_trs_cons_sus_or=3,
nombre_region=3,
tipo_centro_pub=3,
sexo_2=3,
dg_trs_cons_sus_or=3,
edad_al_ing=2,
fech_ing_num=2,
abandono_temprano_rec=3,
evaluacindelprocesoteraputico=3),
data = CONS_C1_df_dup_SEP_2020_match,
include.miss = T,
var.equal=T,
subset= more_one_treat==0)
)
#Possible values are: 1 - for analysis as "normal-distributed"; 2 - forces analysis as "continuous non-normal"; 3 - forces analysis as "categorical"; and 4 - NA, which performs a Shapiro-Wilks test to decide between normal or non-normal.
restab1_all <- createTable(table1_all, show.p.overall = T)
restab1_more_one <- createTable(table1_more_one, show.p.overall = T)
restab1_only_one <- createTable(table1_only_one, show.p.overall = T)
pvals1 <- getResults(table1_all)
#p.adjust(pvals, method = "BH")
export2md(restab1_all, size=10, first.strip=T, hide.no="no", position="center",
format="html",caption= "Table 1. Summary descriptives at baseline, between Users with Residential and Ambulatory Treatments from 2010-2019",col.names=c("Variables","Residential", "Ambulatory", "p-value"))%>%
kableExtra::add_footnote(c("Note. Continuous variables are presented as Medians and Percentiles 25 and 75 were shown;", "Categorical variables are presented as number (%)"), notation = "none")%>%
kableExtra::scroll_box(width = "100%", height = "375px")| Variables | Residential | Ambulatory | p-value |
|---|---|---|---|
| N=72267 | N=12706 | ||
| Starting Substance: | 0.000 | ||
| Alcohol | 41507 (57.4%) | 5080 (40.0%) | |
| Cocaine hydrochloride | 2682 (3.71%) | 477 (3.75%) | |
| Marijuana | 18412 (25.5%) | 4556 (35.9%) | |
| Other | 1669 (2.31%) | 318 (2.50%) | |
| Cocaine paste | 2767 (3.83%) | 1086 (8.55%) | |
| ‘Missing’ | 5230 (7.24%) | 1189 (9.36%) | |
| Marital Status: | <0.001 | ||
| Married/Shared living arrangements | 26185 (36.2%) | 2910 (22.9%) | |
| Separated/Divorced | 7721 (10.7%) | 1320 (10.4%) | |
| Single | 37343 (51.7%) | 8328 (65.5%) | |
| Widower | 869 (1.20%) | 133 (1.05%) | |
| ‘Missing’ | 149 (0.21%) | 15 (0.12%) | |
| Educational Attainment: | <0.001 | ||
| 3-Completed primary school or less | 20062 (27.8%) | 3862 (30.4%) | |
| 2-Completed high school or less | 39565 (54.7%) | 7044 (55.4%) | |
| 1-More than high school | 12279 (17.0%) | 1777 (14.0%) | |
| ‘Missing’ | 361 (0.50%) | 23 (0.18%) | |
| Frequency of use of primary drug: | 0.000 | ||
| Did not use | 1095 (1.52%) | 85 (0.67%) | |
| Less than 1 day a week | 2862 (3.96%) | 133 (1.05%) | |
| 2 to 3 days a week | 22372 (31.0%) | 1329 (10.5%) | |
| 4 to 6 days a week | 12258 (17.0%) | 1654 (13.0%) | |
| 1 day a week or more | 5335 (7.38%) | 272 (2.14%) | |
| Daily | 27938 (38.7%) | 9219 (72.6%) | |
| ‘Missing’ | 407 (0.56%) | 14 (0.11%) | |
| Motive of Admission to Treatment: | 0.000 | ||
| Spontaneous | 33720 (46.7%) | 4273 (33.6%) | |
| Assisted Referral | 4950 (6.85%) | 3013 (23.7%) | |
| Other | 3766 (5.21%) | 740 (5.82%) | |
| Justice Sector | 7159 (9.91%) | 812 (6.39%) | |
| Health Sector | 22672 (31.4%) | 3868 (30.4%) | |
| Psychiatric co-morbidity: | <0.001 | ||
| Without psychiatric comorbidity | 29070 (40.2%) | 3245 (25.5%) | |
| Diagnosis unknown (under study) | 13310 (18.4%) | 2771 (21.8%) | |
| With psychiatric comorbidity | 29887 (41.4%) | 6690 (52.7%) | |
| Type of Center (Public): | 0.000 | ||
| FALSE | 14964 (20.7%) | 9066 (71.4%) | |
| TRUE | 57300 (79.3%) | 3623 (28.5%) | |
| ‘Missing’ | 3 (0.00%) | 17 (0.13%) | |
| Sex: | <0.001 | ||
| Men | 54806 (75.8%) | 8761 (69.0%) | |
| Women | 17461 (24.2%) | 3945 (31.0%) | |
| Drug Dependence: | 0.000 | ||
| FALSE | 22150 (30.7%) | 1049 (8.26%) | |
| TRUE | 50116 (69.3%) | 11657 (91.7%) | |
| ‘Missing’ | 1 (0.00%) | 0 (0.00%) | |
| Age at Admission | 34.5 [27.6;43.5] | 32.6 [26.3;40.9] | <0.001 |
| Date of Admission to Treatment | 16577 [15730;17359] | 16154 [15342;17023] | <0.001 |
| Early Dropout: | <0.001 | ||
| FALSE | 61074 (84.5%) | 10201 (80.3%) | |
| TRUE | 11190 (15.5%) | 2499 (19.7%) | |
| ‘Missing’ | 3 (0.00%) | 6 (0.05%) | |
| No. of Treatments in the Database: | . | ||
| 1 | 58708 (81.2%) | 8533 (67.2%) | |
| 2 | 10087 (14.0%) | 2804 (22.1%) | |
| 3 | 2471 (3.42%) | 927 (7.30%) | |
| 4 | 714 (0.99%) | 295 (2.32%) | |
| 5 | 192 (0.27%) | 94 (0.74%) | |
| 6 | 67 (0.09%) | 36 (0.28%) | |
| 7 | 23 (0.03%) | 11 (0.09%) | |
| 8 | 4 (0.01%) | 6 (0.05%) | |
| 10 | 1 (0.00%) | 0 (0.00%) | |
| Drug Dependence: | 0.000 | ||
| FALSE | 22150 (30.7%) | 1049 (8.26%) | |
| TRUE | 50116 (69.3%) | 11657 (91.7%) | |
| ‘Missing’ | 1 (0.00%) | 0 (0.00%) | |
| Evaluation of the Therapeutic Process: | <0.001 | ||
| 1-High Achievement | 14081 (19.5%) | 2831 (22.3%) | |
| 2-Medium Achievement | 21728 (30.1%) | 4237 (33.3%) | |
| 3-Minimum Achievement | 31549 (43.7%) | 5302 (41.7%) | |
| ‘Missing’ | 4909 (6.79%) | 336 (2.64%) | |
| Note. Continuous variables are presented as Medians and Percentiles 25 and 75 were shown; | |||
| Categorical variables are presented as number (%) |
Of the 85,048 users, we selected 85,048 that fulfilled the conditions stated above (100%).
Additionally, we generated a correlation plot to get an overview of heterogeneous correlations between the different variables.
require(polycor)
#Corresponde a la apreciación clínica que hace el equipo o profesional tratante, la persona en tratamiento y su familia, del nivel alcanzado de logro de los objetivos terapéuticos planteados al inicio del proceso y descritos en el plan de tratamiento personalizado. Los criterios incluyen la evaluación del estado clínico y psicosocial al momento del egreso y una apreciación pronostica del equipo tratante.
#Computes a heterogenous correlation matrix, consisting of Pearson product-moment correlations between numeric variables, polyserial correlations between numeric and ordinal variables, and polychoric correlations between
tiempo_antes_hetcor<-Sys.time()
hetcor_mat<-hetcor(CONS_C1_df_dup_SEP_2020_match[,-c("hash_key","row","more_one_treat","duplicates_filtered")], ML = T, std.err =T, use="pairwise.complete.obs", bins=3, pd=TRUE)
tiempo_despues_hetcor<-Sys.time()
tiempo_hetcor<-tiempo_despues_hetcor-tiempo_antes_hetcor
attr(hetcor_mat$correlations,"dimnames")[[2]][1]<-"Starting Substance"
attr(hetcor_mat$correlations,"dimnames")[[2]][2]<-"Marital Status"
attr(hetcor_mat$correlations,"dimnames")[[2]][3]<-"Educational Attainment"
attr(hetcor_mat$correlations,"dimnames")[[2]][4]<-"Age of Onset of Drug Use"
attr(hetcor_mat$correlations,"dimnames")[[2]][5]<-"Frequency of use of primary drug"
attr(hetcor_mat$correlations,"dimnames")[[2]][6]<-"Motive of Admission to Treatment"
attr(hetcor_mat$correlations,"dimnames")[[2]][7]<-"Psychiatric comorbidity"
#attr(hetcor_mat$correlations,"dimnames")[[2]][8]<-"Physical comorbidity"
attr(hetcor_mat$correlations,"dimnames")[[2]][8]<-"Chilean Region of the Center"
attr(hetcor_mat$correlations,"dimnames")[[2]][9]<-"Type of Center (Public)"
attr(hetcor_mat$correlations,"dimnames")[[2]][10]<-"Sex"
attr(hetcor_mat$correlations,"dimnames")[[2]][11]<-"Age at Admission"
attr(hetcor_mat$correlations,"dimnames")[[2]][12]<-"Date of Admission"
attr(hetcor_mat$correlations,"dimnames")[[2]][13]<-"Early Drop out"
attr(hetcor_mat$correlations,"dimnames")[[2]][14]<-"Residential Treatment"
attr(hetcor_mat$correlations,"dimnames")[[2]][15]<-"Drug Dependence"
attr(hetcor_mat$correlations,"dimnames")[[2]][16]<-"Evaluation of the Therapeutic Process"
attr(hetcor_mat$correlations,"dimnames")[[1]][1]<-"Starting Substance"
attr(hetcor_mat$correlations,"dimnames")[[1]][2]<-"Marital Status"
attr(hetcor_mat$correlations,"dimnames")[[1]][3]<-"Educational Attainment"
attr(hetcor_mat$correlations,"dimnames")[[1]][4]<-"Age of Onset of Drug Use"
attr(hetcor_mat$correlations,"dimnames")[[1]][5]<-"Frequency of use of primary drug"
attr(hetcor_mat$correlations,"dimnames")[[1]][6]<-"Motive of Admission to Treatment"
attr(hetcor_mat$correlations,"dimnames")[[1]][7]<-"Psychiatric comorbidity"
#attr(hetcor_mat$correlations,"dimnames")[[1]][8]<-"Physical comorbidity"
attr(hetcor_mat$correlations,"dimnames")[[1]][8]<-"Chilean Region of the Center"
attr(hetcor_mat$correlations,"dimnames")[[1]][9]<-"Type of Center (Public)"
attr(hetcor_mat$correlations,"dimnames")[[1]][10]<-"Sex"
attr(hetcor_mat$correlations,"dimnames")[[1]][11]<-"Age at Admission"
attr(hetcor_mat$correlations,"dimnames")[[1]][12]<-"Date of Admission"
attr(hetcor_mat$correlations,"dimnames")[[1]][13]<-"Early Drop out"
attr(hetcor_mat$correlations,"dimnames")[[1]][14]<-"Residential Treatment"
attr(hetcor_mat$correlations,"dimnames")[[1]][15]<-"Drug Dependence"
attr(hetcor_mat$correlations,"dimnames")[[1]][16]<-"Evaluation of the Therapeutic Process"
attr(hetcor_mat$tests,"dimnames")[[2]][1]<-"Starting Substance"
attr(hetcor_mat$tests,"dimnames")[[2]][2]<-"Marital Status"
attr(hetcor_mat$tests,"dimnames")[[2]][3]<-"Educational Attainment"
attr(hetcor_mat$tests,"dimnames")[[2]][4]<-"Age of Onset of Drug Use"
attr(hetcor_mat$tests,"dimnames")[[2]][5]<-"Frequency of use of primary drug"
attr(hetcor_mat$tests,"dimnames")[[2]][6]<-"Motive of Admission to Treatment"
attr(hetcor_mat$tests,"dimnames")[[2]][7]<-"Psychiatric comorbidity"
#attr(hetcor_mat$tests,"dimnames")[[2]][8]<-"Physical comorbidity"
attr(hetcor_mat$tests,"dimnames")[[2]][8]<-"Chilean Region of the Center"
attr(hetcor_mat$tests,"dimnames")[[2]][9]<-"Type of Center (Public)"
attr(hetcor_mat$tests,"dimnames")[[2]][10]<-"Sex"
attr(hetcor_mat$tests,"dimnames")[[2]][11]<-"Age at Admission"
attr(hetcor_mat$tests,"dimnames")[[2]][12]<-"Date of Admission"
attr(hetcor_mat$tests,"dimnames")[[2]][13]<-"Early Drop out"
attr(hetcor_mat$tests,"dimnames")[[2]][14]<-"Residential Treatment"
attr(hetcor_mat$tests,"dimnames")[[2]][15]<-"Drug Dependence"
attr(hetcor_mat$tests,"dimnames")[[2]][16]<-"Evaluation of the Therapeutic Process"
attr(hetcor_mat$tests,"dimnames")[[1]][1]<-"Starting Substance"
attr(hetcor_mat$tests,"dimnames")[[1]][2]<-"Marital Status"
attr(hetcor_mat$tests,"dimnames")[[1]][3]<-"Educational Attainment"
attr(hetcor_mat$tests,"dimnames")[[1]][4]<-"Age of Onset of Drug Use"
attr(hetcor_mat$tests,"dimnames")[[1]][5]<-"Frequency of use of primary drug"
attr(hetcor_mat$tests,"dimnames")[[1]][6]<-"Motive of Admission to Treatment"
attr(hetcor_mat$tests,"dimnames")[[1]][7]<-"Psychiatric comorbidity"
#attr(hetcor_mat$tests,"dimnames")[[1]][8]<-"Physical comorbidity"
attr(hetcor_mat$tests,"dimnames")[[1]][8]<-"Chilean Region of the Center"
attr(hetcor_mat$tests,"dimnames")[[1]][9]<-"Type of Center (Public)"
attr(hetcor_mat$tests,"dimnames")[[1]][10]<-"Sex"
attr(hetcor_mat$tests,"dimnames")[[1]][11]<-"Age at Admission"
attr(hetcor_mat$tests,"dimnames")[[1]][12]<-"Date of Admission"
attr(hetcor_mat$tests,"dimnames")[[1]][13]<-"Early Drop out"
attr(hetcor_mat$tests,"dimnames")[[1]][14]<-"Residential Treatment"
attr(hetcor_mat$tests,"dimnames")[[1]][15]<-"Drug Dependence"
attr(hetcor_mat$tests,"dimnames")[[1]][16]<-"Evaluation of the Therapeutic Process"
hetcor_mat$tests[is.na(hetcor_mat$tests)]<-1
ggcorrplot<-
ggcorrplot::ggcorrplot(hetcor_mat$correlations,
ggtheme = ggplot2::theme_void,
insig = "blank",
pch=1,
pch.cex=3,
tl.srt = 45,
#pch="ns",
p.mat = hetcor_mat$tests, # replacement has 144 rows, data has 169
#type = "lower",
colors = c("#6D9EC1", "white", "#E46726"),
tl.cex=8,
lab=F)+
#scale_x_discrete(labels = var_lbls_p345, drop = F) +
#scale_y_discrete(labels = var_lbls_p345, drop = F) +
theme(axis.text.x = element_blank())+
#theme(axis.text.y = element_text(size=7.5,color ="black", hjust = 1))+
theme(axis.text.y = element_blank())+
theme(legend.position="bottom")
ggplotly(ggcorrplot, height = 800, width=800)%>%
layout(xaxis= list(showticklabels = FALSE)) %>%
layout(annotations =
list(x = .1, y = -0.031, text = "",
showarrow = F, xref='paper', yref='paper',
#xanchor='center', yanchor='auto', xshift=0, yshift=-0,
font=list(size=11, color="darkblue"))
)Figure 2. Heterogeneous Correlation Matrix of Variables of Interest
Imputation
We generated a plot to see all the missing values in the sample.
Figure 3. Bar plot of Porcentaje of Missing Values per Variables at Basline
From the figure above, we could see that the starting substance (sus_ini_mvv), the onset of drug use (edad_ini_cons) and the evaluation of the therapeutic process (evaluacindelprocesoteraputico) had around 6% of missing data. These values should be imputed. We first focused on the age of onset of drug use. It is important to consider that the evaluation of the therapeutic process could be distorted due to censoring (many users did not finish their treatment, and did not have this evaluation in the study period).
Age at Admission
We started looking over the missing values in the age at admission (n8). Since there were not cases with more than one treatment that had not an age of admission, we did not have to impute taking into account serial dependencies in the dates of treatment.
Figure 5. Density Estimation of Distributions of Age at Admission & Imputed Age at Admission
As seen in the Figure above, distributions seem to differ. However, considering the low amount of missing values in this variable, we proceeded with the imputation with the mean, despite the differences found. The imputed values must not be greater than the age of onset of drug use and may not be lower than 16 years old. Values lower than this age may be considered less likely to receive treatment for adult population, so it would be most probably incorrect that they would be in this database.
## [1] "Users that had more than one treatment with no date of admission:0"Age of Onset of Drug Use
Another variable worth imputing is the Age of Onset of Drug Use (n= 6,549).
Figure 6. Density Estimation of Distributions of Age Of Onset of Drug Use & Imputed Ones
Based on the figure above, the age of onset of drug use was similar between the imputed values and the observed. However, we followed the rules stated in Duplicates process (link). There were three logical conditions to fulfill in order to replace adequately these values in the database: the age of onset must not be greater than the age of onset of drug use in the primary substance at admission (1), may not be greater than the age of admission to treatment (2), and the age of onset of drug use must be greater than 4 years old. Then, we selected the minimum value of age of onset of drug use among the imputed, because one user could not have more than one age of onset of drug use.
## [1] "Number of users that had more than one different age of onset of drug use before replacement: 0"Figure 7. Bar plot of Percentage of Incorrect Imputed Values per Imputation Sample
## [1] "Cases with more than missing one age of onset: 515"## [1] "Number of rows with values that did not fulfilled the conditions: 0"## [1] "Number of rows with values that did not fulfilled the conditions after replacement with the minimum by users: 0"## [1] "Number of users that had different age of onset of drug use after replacement: 0"There were 0 cases of imputed ages of onset of drug use that did not fulfilled the conditions necessary to replace the missing values with the imputed ones.
Starting Substance
Then we selected the most vulnerable value among the candidates of imputations of the starting substance (First, Cocaine paste, Cocaine hydrochloride or snort cocaine, Marijuana, Alcohol, and Other).
# Ver distintos valores propuestos para sustancia de inciio
sus_ini_mod_mvv_imputed<-
cbind.data.frame(amelia_fit$imputations$imp1$row,
amelia_fit$imputations$imp1$sus_ini_mod_mvv,
amelia_fit$imputations$imp2$sus_ini_mod_mvv,
amelia_fit$imputations$imp3$sus_ini_mod_mvv,
amelia_fit$imputations$imp4$sus_ini_mod_mvv,
amelia_fit$imputations$imp5$sus_ini_mod_mvv,
amelia_fit$imputations$imp6$sus_ini_mod_mvv,
amelia_fit$imputations$imp7$sus_ini_mod_mvv,
amelia_fit$imputations$imp8$sus_ini_mod_mvv,
amelia_fit$imputations$imp9$sus_ini_mod_mvv,
amelia_fit$imputations$imp10$sus_ini_mod_mvv,
amelia_fit$imputations$imp11$sus_ini_mod_mvv,
amelia_fit$imputations$imp12$sus_ini_mod_mvv,
amelia_fit$imputations$imp13$sus_ini_mod_mvv,
amelia_fit$imputations$imp14$sus_ini_mod_mvv,
amelia_fit$imputations$imp15$sus_ini_mod_mvv,
amelia_fit$imputations$imp16$sus_ini_mod_mvv,
amelia_fit$imputations$imp17$sus_ini_mod_mvv,
amelia_fit$imputations$imp18$sus_ini_mod_mvv,
amelia_fit$imputations$imp19$sus_ini_mod_mvv,
amelia_fit$imputations$imp20$sus_ini_mod_mvv,
amelia_fit$imputations$imp21$sus_ini_mod_mvv,
amelia_fit$imputations$imp22$sus_ini_mod_mvv,
amelia_fit$imputations$imp23$sus_ini_mod_mvv,
amelia_fit$imputations$imp24$sus_ini_mod_mvv,
amelia_fit$imputations$imp25$sus_ini_mod_mvv,
amelia_fit$imputations$imp26$sus_ini_mod_mvv,
amelia_fit$imputations$imp27$sus_ini_mod_mvv,
amelia_fit$imputations$imp28$sus_ini_mod_mvv,
amelia_fit$imputations$imp29$sus_ini_mod_mvv,
amelia_fit$imputations$imp30$sus_ini_mod_mvv
)
sus_ini_mod_mvv_imputed<-
sus_ini_mod_mvv_imputed %>%
data.frame() %>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.sus_ini_mod_mvv:amelia_fit.imputations.imp30.sus_ini_mod_mvv),~dplyr::case_when(grepl("Marijuana",as.character(.))~1,TRUE~0), .names="mar_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.sus_ini_mod_mvv:amelia_fit.imputations.imp30.sus_ini_mod_mvv),~dplyr::case_when(grepl("Alcohol",as.character(.))~1,TRUE~0), .names="oh_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.sus_ini_mod_mvv:amelia_fit.imputations.imp30.sus_ini_mod_mvv),~dplyr::case_when(grepl("Cocaine paste",as.character(.))~1,TRUE~0), .names="pb_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.sus_ini_mod_mvv:amelia_fit.imputations.imp30.sus_ini_mod_mvv),~dplyr::case_when(grepl("Cocaine hydrochloride",as.character(.))~1,TRUE~0), .names="coc_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.sus_ini_mod_mvv:amelia_fit.imputations.imp30.sus_ini_mod_mvv),~dplyr::case_when(grepl("Other",as.character(.))~1,TRUE~0), .names="otr_{col}"))%>%
dplyr::mutate(sus_ini_mod_mvv_mar = base::rowSums(dplyr::select(., starts_with("mar_"))))%>%
dplyr::mutate(sus_ini_mod_mvv_oh = base::rowSums(dplyr::select(., starts_with("oh_"))))%>%
dplyr::mutate(sus_ini_mod_mvv_pb = base::rowSums(dplyr::select(., starts_with("pb_"))))%>%
dplyr::mutate(sus_ini_mod_mvv_coc = base::rowSums(dplyr::select(., starts_with("coc_"))))%>%
dplyr::mutate(sus_ini_mod_mvv_otr = base::rowSums(dplyr::select(., starts_with("otr_")))) %>%
#dplyr::summarise(min_mar=max(sus_ini_mod_mvv_mar[sus_ini_mod_mvv_mar<30]),min_oh=max(sus_ini_mod_mvv_oh[sus_ini_mod_mvv_oh<30]),min_pb=max(sus_ini_mod_mvv_pb[sus_ini_mod_mvv_pb<30]),min_coc=max(sus_ini_mod_mvv_coc[sus_ini_mod_mvv_coc<30]),min_otr=max(sus_ini_mod_mvv_otr[sus_ini_mod_mvv_otr<30]))
dplyr::mutate(sus_ini_mod_mvv_tot=dplyr::case_when(sus_ini_mod_mvv_mar>0~1,TRUE~0)) %>%
dplyr::mutate(sus_ini_mod_mvv_tot=dplyr::case_when(sus_ini_mod_mvv_oh>0~sus_ini_mod_mvv_tot+1,TRUE~sus_ini_mod_mvv_tot)) %>%
dplyr::mutate(sus_ini_mod_mvv_tot=dplyr::case_when(sus_ini_mod_mvv_pb>0~sus_ini_mod_mvv_tot+1,TRUE~sus_ini_mod_mvv_tot)) %>%
dplyr::mutate(sus_ini_mod_mvv_tot=dplyr::case_when(sus_ini_mod_mvv_coc>0~sus_ini_mod_mvv_tot+1,TRUE~sus_ini_mod_mvv_tot)) %>%
dplyr::mutate(sus_ini_mod_mvv_tot=dplyr::case_when(sus_ini_mod_mvv_otr>0~sus_ini_mod_mvv_tot+1,TRUE~sus_ini_mod_mvv_tot)) %>%
dplyr::mutate(sus_ini_mod_mvv_to_imputation=dplyr::case_when(sus_ini_mod_mvv_tot==1 & sus_ini_mod_mvv_pb>0~"Cocaine paste",sus_ini_mod_mvv_tot==1 & sus_ini_mod_mvv_coc>0~"Cocaine hydrochloride",sus_ini_mod_mvv_tot==1 & sus_ini_mod_mvv_mar>0~"Marijuana",sus_ini_mod_mvv_tot==1 & sus_ini_mod_mvv_oh>0~"Alcohol",sus_ini_mod_mvv_tot==1 & sus_ini_mod_mvv_otr>0~"Other",sus_ini_mod_mvv_tot>1 & sus_ini_mod_mvv_pb>0~"Cocaine paste",sus_ini_mod_mvv_tot>1 & sus_ini_mod_mvv_coc>0~"Cocaine hydrochloride",sus_ini_mod_mvv_tot>1 & sus_ini_mod_mvv_mar>0~"Marijuana",sus_ini_mod_mvv_tot>1 & sus_ini_mod_mvv_oh>0~"Alcohol",sus_ini_mod_mvv_tot>1 & sus_ini_mod_mvv_otr>0~"Other")) %>%
janitor::clean_names()
sus_ini_mod_mvv_imputed<-
dplyr::select(sus_ini_mod_mvv_imputed,amelia_fit_imputations_imp1_row,sus_ini_mod_mvv_to_imputation)
#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:
CONS_C1_df_dup_SEP_2020_match_miss2<-
CONS_C1_df_dup_SEP_2020_match_miss1 %>%
dplyr::left_join(sus_ini_mod_mvv_imputed, by=c("row"="amelia_fit_imputations_imp1_row")) %>%
dplyr::mutate(sus_ini_mod_mvv=factor(dplyr::case_when(is.na(sus_ini_mod_mvv)~as.character(sus_ini_mod_mvv_to_imputation),
TRUE~as.character(sus_ini_mod_mvv)))) %>%
dplyr::select(-sus_ini_mod_mvv_to_imputation) %>%
data.table()
#_#_#_#_#_#_#__#_##_#_#_#_#_#_#_#_#_#_#_#_#__#_##_#_#_#_#_##_#_#_#_#_#_#__#_##_#_#_#_#_#_#_#_#_#_#_#_#__#_##_#_#_#_#_#
#_#_#_#_#_#_#__#_##_#_#_#_#_#_#_#_#_#_#_#_#__#_##_#_#_#_#_##_#_#_#_#_#_#__#_##_#_#_#_#_#_#_#_#_#_#_#_#__#_##_#_#_#_#_#Frequency of Use of the Primary Drug at Admission
Another variable that is worth imputing is the Frequency of use of primary drug at admission (n= 568). In case of ties, we selected the imputed values with the value with the most frequent drug use.
# Ver distintos valores propuestos para sustancia de inciio
freq_cons_sus_prin_imputed<-
cbind.data.frame(amelia_fit$imputations$imp1$row,
amelia_fit$imputations$imp1$freq_cons_sus_prin,
amelia_fit$imputations$imp2$freq_cons_sus_prin,
amelia_fit$imputations$imp3$freq_cons_sus_prin,
amelia_fit$imputations$imp4$freq_cons_sus_prin,
amelia_fit$imputations$imp5$freq_cons_sus_prin,
amelia_fit$imputations$imp6$freq_cons_sus_prin,
amelia_fit$imputations$imp7$freq_cons_sus_prin,
amelia_fit$imputations$imp8$freq_cons_sus_prin,
amelia_fit$imputations$imp9$freq_cons_sus_prin,
amelia_fit$imputations$imp10$freq_cons_sus_prin,
amelia_fit$imputations$imp11$freq_cons_sus_prin,
amelia_fit$imputations$imp12$freq_cons_sus_prin,
amelia_fit$imputations$imp13$freq_cons_sus_prin,
amelia_fit$imputations$imp14$freq_cons_sus_prin,
amelia_fit$imputations$imp15$freq_cons_sus_prin,
amelia_fit$imputations$imp16$freq_cons_sus_prin,
amelia_fit$imputations$imp17$freq_cons_sus_prin,
amelia_fit$imputations$imp18$freq_cons_sus_prin,
amelia_fit$imputations$imp19$freq_cons_sus_prin,
amelia_fit$imputations$imp20$freq_cons_sus_prin,
amelia_fit$imputations$imp21$freq_cons_sus_prin,
amelia_fit$imputations$imp22$freq_cons_sus_prin,
amelia_fit$imputations$imp23$freq_cons_sus_prin,
amelia_fit$imputations$imp24$freq_cons_sus_prin,
amelia_fit$imputations$imp25$freq_cons_sus_prin,
amelia_fit$imputations$imp26$freq_cons_sus_prin,
amelia_fit$imputations$imp27$freq_cons_sus_prin,
amelia_fit$imputations$imp28$freq_cons_sus_prin,
amelia_fit$imputations$imp29$freq_cons_sus_prin,
amelia_fit$imputations$imp30$freq_cons_sus_prin
)
freq_cons_sus_prin_imputed<-
freq_cons_sus_prin_imputed %>%
data.frame() %>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.freq_cons_sus_prin:amelia_fit.imputations.imp30.freq_cons_sus_prin),~dplyr::case_when(grepl("1 day a week or more",as.character(.))~1,TRUE~0), .names="1_day_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.freq_cons_sus_prin:amelia_fit.imputations.imp30.freq_cons_sus_prin),~dplyr::case_when(grepl("2 to 3 days a week",as.character(.))~1,TRUE~0), .names="2_3_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.freq_cons_sus_prin:amelia_fit.imputations.imp30.freq_cons_sus_prin),~dplyr::case_when(grepl("4 to 6 days a week",as.character(.))~1,TRUE~0), .names="4_6_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.freq_cons_sus_prin:amelia_fit.imputations.imp30.freq_cons_sus_prin),~dplyr::case_when(grepl("Less than 1 day a week",as.character(.))~1,TRUE~0), .names="less_1_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.freq_cons_sus_prin:amelia_fit.imputations.imp30.freq_cons_sus_prin),~dplyr::case_when(grepl("Did not use",as.character(.))~1,TRUE~0), .names="did_not_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.freq_cons_sus_prin:amelia_fit.imputations.imp30.freq_cons_sus_prin),~dplyr::case_when(grepl("Daily",as.character(.))~1,TRUE~0), .names="daily_{col}"))%>%
dplyr::mutate(freq_cons_sus_prin_daily = base::rowSums(dplyr::select(., starts_with("daily_")))) %>%
dplyr::mutate(freq_cons_sus_prin_4_6 = base::rowSums(dplyr::select(., starts_with("4_6_"))))%>%
dplyr::mutate(freq_cons_sus_prin_2_3 = base::rowSums(dplyr::select(., starts_with("2_3_"))))%>%
dplyr::mutate(freq_cons_sus_prin_1_day = base::rowSums(dplyr::select(., starts_with("1_day_"))))%>%
dplyr::mutate(freq_cons_sus_prin_less_1 = base::rowSums(dplyr::select(., starts_with("less_1_"))))%>%
dplyr::mutate(freq_cons_sus_prin_did_not = base::rowSums(dplyr::select(., starts_with("did_not_")))) %>%
#dplyr::summarise(min_mar=max(sus_ini_mod_mvv_mar[sus_ini_mod_mvv_mar<30]),min_oh=max(sus_ini_mod_mvv_oh[sus_ini_mod_mvv_oh<30]),min_pb=max(sus_ini_mod_mvv_pb[sus_ini_mod_mvv_pb<30]),min_coc=max(sus_ini_mod_mvv_coc[sus_ini_mod_mvv_coc<30]),min_otr=max(sus_ini_mod_mvv_otr[sus_ini_mod_mvv_otr<30]))
dplyr::mutate(freq_cons_sus_prin_tot=dplyr::case_when(freq_cons_sus_prin_1_day>0~1,TRUE~0)) %>%
dplyr::mutate(freq_cons_sus_prin_tot=dplyr::case_when(freq_cons_sus_prin_2_3>0~freq_cons_sus_prin_tot+1,TRUE~freq_cons_sus_prin_tot)) %>%
dplyr::mutate(freq_cons_sus_prin_tot=dplyr::case_when(freq_cons_sus_prin_4_6>0~freq_cons_sus_prin_tot+1,TRUE~freq_cons_sus_prin_tot)) %>%
dplyr::mutate(freq_cons_sus_prin_tot=dplyr::case_when(freq_cons_sus_prin_less_1>0~freq_cons_sus_prin_tot+1,TRUE~freq_cons_sus_prin_tot)) %>%
dplyr::mutate(freq_cons_sus_prin_tot=dplyr::case_when(freq_cons_sus_prin_did_not>0~freq_cons_sus_prin_tot+1,TRUE~freq_cons_sus_prin_tot)) %>%
dplyr::mutate(freq_cons_sus_prin_tot=dplyr::case_when(freq_cons_sus_prin_daily>0~freq_cons_sus_prin_tot+1,TRUE~freq_cons_sus_prin_tot)) %>%
#hierarchy
dplyr::mutate(freq_cons_sus_prin_to_imputation=
dplyr::case_when(freq_cons_sus_prin_tot==1 & freq_cons_sus_prin_daily>0~"Daily",
freq_cons_sus_prin_tot==1 & freq_cons_sus_prin_4_6>0~"4 to 6 days a week",freq_cons_sus_prin_tot==1 & freq_cons_sus_prin_2_3>0~"2 to 3 days a week",freq_cons_sus_prin_tot==1 & freq_cons_sus_prin_1_day>0~"1 day a week or more",freq_cons_sus_prin_tot==1 & freq_cons_sus_prin_less_1>0~"Less than 1 day a week",freq_cons_sus_prin_tot==1 & freq_cons_sus_prin_did_not>0~"Did not use",freq_cons_sus_prin_tot>1 & freq_cons_sus_prin_daily>0~"Daily",freq_cons_sus_prin_tot>1 & freq_cons_sus_prin_4_6>0~"4 to 6 days a week",freq_cons_sus_prin_tot>1 & freq_cons_sus_prin_2_3>0~"2 to 3 days a week",freq_cons_sus_prin_tot>1 & freq_cons_sus_prin_1_day>0~"1 day a week or more",freq_cons_sus_prin_tot>1 & freq_cons_sus_prin_less_1>0~"Less than 1 day a week",freq_cons_sus_prin_tot>1 & freq_cons_sus_prin_did_not>0~"Did not use")) %>%
janitor::clean_names()
freq_cons_sus_prin_imputed<-
dplyr::select(freq_cons_sus_prin_imputed,amelia_fit_imputations_imp1_row,freq_cons_sus_prin_to_imputation)
#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:
CONS_C1_df_dup_SEP_2020_match_miss3<-
CONS_C1_df_dup_SEP_2020_match_miss2 %>%
dplyr::left_join(freq_cons_sus_prin_imputed, by=c("row"="amelia_fit_imputations_imp1_row")) %>%
dplyr::mutate(freq_cons_sus_prin=factor(dplyr::case_when(is.na(freq_cons_sus_prin)~as.character(freq_cons_sus_prin_to_imputation), TRUE~as.character(freq_cons_sus_prin)))) %>%
data.table()Educational Attainment
Another variable that is worth imputing is the Educational Attainment (n= 437). we followed the rules stated in Duplicates4 process (link). We were particularly cautious to impute attainments that would follow a progression from primary school to more than high school. For this purpose, we first looked over the actual values per user, filling intermediate gaps in educational attainment in users with intermediate null values (a), we overcame with the difficulty of the incorrect imputations, by logically selecting if there were any .
# Ver distintos valores propuestos para sustancia de inciio
escolaridad_rec_imputed<-
cbind.data.frame(amelia_fit$imputations$imp1$row,
amelia_fit$imputations$imp1$hash_key,
amelia_fit$imputations$imp1$fech_ing_num,
amelia_fit$imputations$imp1$escolaridad_rec,
amelia_fit$imputations$imp2$escolaridad_rec,
amelia_fit$imputations$imp3$escolaridad_rec,
amelia_fit$imputations$imp4$escolaridad_rec,
amelia_fit$imputations$imp5$escolaridad_rec,
amelia_fit$imputations$imp6$escolaridad_rec,
amelia_fit$imputations$imp7$escolaridad_rec,
amelia_fit$imputations$imp8$escolaridad_rec,
amelia_fit$imputations$imp9$escolaridad_rec,
amelia_fit$imputations$imp10$escolaridad_rec,
amelia_fit$imputations$imp11$escolaridad_rec,
amelia_fit$imputations$imp12$escolaridad_rec,
amelia_fit$imputations$imp13$escolaridad_rec,
amelia_fit$imputations$imp14$escolaridad_rec,
amelia_fit$imputations$imp15$escolaridad_rec,
amelia_fit$imputations$imp16$escolaridad_rec,
amelia_fit$imputations$imp17$escolaridad_rec,
amelia_fit$imputations$imp18$escolaridad_rec,
amelia_fit$imputations$imp19$escolaridad_rec,
amelia_fit$imputations$imp20$escolaridad_rec,
amelia_fit$imputations$imp21$escolaridad_rec,
amelia_fit$imputations$imp22$escolaridad_rec,
amelia_fit$imputations$imp23$escolaridad_rec,
amelia_fit$imputations$imp24$escolaridad_rec,
amelia_fit$imputations$imp25$escolaridad_rec,
amelia_fit$imputations$imp26$escolaridad_rec,
amelia_fit$imputations$imp27$escolaridad_rec,
amelia_fit$imputations$imp28$escolaridad_rec,
amelia_fit$imputations$imp29$escolaridad_rec,
amelia_fit$imputations$imp30$escolaridad_rec)
escolaridad_rec_imputed2<-
escolaridad_rec_imputed %>%
data.frame() %>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.escolaridad_rec:amelia_fit.imputations.imp30.escolaridad_rec),~dplyr::case_when(grepl("3-Completed primary school or less",as.character(.))~1,TRUE~0), .names="3_primary_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.escolaridad_rec:amelia_fit.imputations.imp30.escolaridad_rec),~dplyr::case_when(grepl("2-Completed high school or less",as.character(.))~1,TRUE~0), .names="2_high_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.escolaridad_rec:amelia_fit.imputations.imp30.escolaridad_rec),~dplyr::case_when(grepl("1-More than high school",as.character(.))~1,TRUE~0), .names="1_more_high_{col}")) %>%
dplyr::mutate(escolaridad_rec_3_primary = base::rowSums(dplyr::select(., contains("3_primary_")))) %>%
dplyr::mutate(escolaridad_rec_2_high = base::rowSums(dplyr::select(., contains("2_high_"))))%>%
dplyr::mutate(escolaridad_rec_1_more_high = base::rowSums(dplyr::select(., contains("1_more_high_"))))
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
#create an ordered index of the number of treatments by user
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
#:#:#:#;#;#;
CONS_C1_df_dup_SEP_2020_match_rn<-
CONS_C1_df_dup_SEP_2020_match_miss %>% #base de datos original, sin imputaciones
dplyr::group_by(hash_key) %>%
dplyr::mutate(rn=row_number()) %>%
dplyr::ungroup() %>%
dplyr::select(rn)
#:#:#:#;#;#;
escolaridad_rec_imputed3<-
escolaridad_rec_imputed2 %>%
dplyr::left_join(cbind.data.frame(CONS_C1_df_dup_SEP_2020_match_miss$row, CONS_C1_df_dup_SEP_2020_match_miss$escolaridad_rec,CONS_C1_df_dup_SEP_2020_match_rn$rn),by=c("amelia_fit.imputations.imp1.row"="CONS_C1_df_dup_SEP_2020_match_miss$row")) %>%
dplyr::rename("escolaridad_rec_original"="CONS_C1_df_dup_SEP_2020_match_miss$escolaridad_rec") %>%
dplyr::mutate(escolaridad_rec_original=as.numeric(substr(escolaridad_rec_original, 1, 1))) %>%
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
#ordenar por tratamientos por usuario
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
dplyr::arrange(amelia_fit.imputations.imp1.hash_key,`CONS_C1_df_dup_SEP_2020_match_rn$rn`) %>%
dplyr::group_by(amelia_fit.imputations.imp1.hash_key) %>%
dplyr::mutate(siguiente_escolaridad_rec_original=lead(escolaridad_rec_original),
subsig_escolaridad_rec_original=lead(escolaridad_rec_original,n =2),
rn=max(`CONS_C1_df_dup_SEP_2020_match_rn$rn`),
n_na_esc_or=is.na(escolaridad_rec_original),
sum_n_na_esc_or=sum(n_na_esc_or,na.rm=T),
max_sum_n_na_esc_or=max(n_na_esc_or,na.rm=T)
) %>%
#dplyr::select(amelia_fit.imputations.imp1.hash_key,amelia_fit.imputations.imp30.rn,
# siguiente_escolaridad_rec_original,escolaridad_rec_original,amelia_fit.imputations.imp1.fech_ing_num)%>% View()
dplyr::ungroup()
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
#PREPARACIÓN BASE DE DATOS PARA IMPUTACION Y CREACIÓN DE VARIABLES PARA CONDICIONES
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
escolaridad_rec_imputed4 <-
escolaridad_rec_imputed3 %>%
dplyr::select(amelia_fit.imputations.imp1.hash_key,`CONS_C1_df_dup_SEP_2020_match_rn$rn`,escolaridad_rec_original,escolaridad_rec_3_primary,escolaridad_rec_2_high, escolaridad_rec_1_more_high) %>%
dplyr::rename("hash_key"="amelia_fit.imputations.imp1.hash_key") %>%
dplyr::rename("treat_no_for_usr"="CONS_C1_df_dup_SEP_2020_match_rn$rn") %>%
dplyr::group_by(hash_key) %>%
dplyr::mutate(treat_per_usr=max(treat_no_for_usr,na.rm=T)) %>%
dplyr::ungroup() %>%
tidyr::pivot_wider(names_from=treat_no_for_usr,
#names_glue = "ord_treat_esc_{.value}",
values_from=c(escolaridad_rec_original,escolaridad_rec_3_primary,escolaridad_rec_2_high,escolaridad_rec_1_more_high),values_fill = NA) %>%
#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:
#Ver si existen inconsistencias en la escolaridad, pero no sólo inconsistencias inmediatas, sino con hasta 2 espacios entre tratamientos
#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:
#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:
dplyr::mutate(escolaridad_rec_tot_cond=dplyr::case_when(
(escolaridad_rec_original_10>escolaridad_rec_original_9)|(escolaridad_rec_original_10>escolaridad_rec_original_8)|(escolaridad_rec_original_10>escolaridad_rec_original_7)|
(escolaridad_rec_original_9>escolaridad_rec_original_8)|(escolaridad_rec_original_9>escolaridad_rec_original_7)|(escolaridad_rec_original_9>escolaridad_rec_original_6)|
(escolaridad_rec_original_8>escolaridad_rec_original_7)|(escolaridad_rec_original_8>escolaridad_rec_original_6)|(escolaridad_rec_original_8>escolaridad_rec_original_5)|
(escolaridad_rec_original_7>escolaridad_rec_original_6)|(escolaridad_rec_original_7>escolaridad_rec_original_5)|(escolaridad_rec_original_7>escolaridad_rec_original_4)|
(escolaridad_rec_original_6>escolaridad_rec_original_5)|(escolaridad_rec_original_6>escolaridad_rec_original_4)|(escolaridad_rec_original_6>escolaridad_rec_original_3)|
(escolaridad_rec_original_5>escolaridad_rec_original_4)|(escolaridad_rec_original_5>escolaridad_rec_original_3)|(escolaridad_rec_original_5>escolaridad_rec_original_2)|
(escolaridad_rec_original_4>escolaridad_rec_original_3)|(escolaridad_rec_original_4>escolaridad_rec_original_2)|(escolaridad_rec_original_4>escolaridad_rec_original_1)|
(escolaridad_rec_original_3>escolaridad_rec_original_2)|(escolaridad_rec_original_3>escolaridad_rec_original_1)|
(escolaridad_rec_original_2>escolaridad_rec_original_1)~1,TRUE~0)) %>%
#dplyr::filter(escolaridad_rec_tot_cond==1) %>% #View() #0 rows ¿y 374745c85601976177fe614a7370e475?
#dplyr::filter(treat_per_usr>1) %>%
#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:
# Ver si hay valores de escolaridad ausentes en una progresión de tratamientos
#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:
dplyr::mutate(sum_nas_esc=base::rowSums(is.na(dplyr::select(., starts_with("escolaridad_rec_original_")))))%>%
dplyr::mutate(escolaridad_rec_tot_nas_en_medio=dplyr::case_when(
(sum_nas_esc>10 & treat_per_usr==10)|
(sum_nas_esc>1 & treat_per_usr==9)|
(sum_nas_esc>2 & treat_per_usr==8)|
(sum_nas_esc>3 & treat_per_usr==7)|
(sum_nas_esc>4 & treat_per_usr==6)|
(sum_nas_esc>5 & treat_per_usr==5)|
(sum_nas_esc>6 & treat_per_usr==4)|
(sum_nas_esc>7 & treat_per_usr==3)|
(sum_nas_esc>8 & treat_per_usr==2)|
(sum_nas_esc>9 & treat_per_usr==1)~1,TRUE~0)) %>% #18b1f9646a2cd6bebd962637cff0a21a 5 casos
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
#Generar la escolaridad al final
#:#:#:#:#:#:#:#:#
dplyr::mutate(last_esc=dplyr::case_when(treat_per_usr==10~escolaridad_rec_original_10,
treat_per_usr==9~escolaridad_rec_original_9,
treat_per_usr==8~escolaridad_rec_original_8,
treat_per_usr==7~escolaridad_rec_original_7,
treat_per_usr==6~escolaridad_rec_original_6,
treat_per_usr==5~escolaridad_rec_original_5,
treat_per_usr==4~escolaridad_rec_original_4,
treat_per_usr==3~escolaridad_rec_original_3,
treat_per_usr==2~escolaridad_rec_original_2,
treat_per_usr==1~escolaridad_rec_original_1)) %>%
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
#a0))si valor final vs. inicial son iguales, imputar todo lo que está en medio con el mismo valor
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
dplyr::mutate(escolaridad_rec_original_9=
dplyr::case_when(escolaridad_rec_original_1==last_esc & treat_per_usr>9 & !is.na(escolaridad_rec_original_1)~escolaridad_rec_original_1,
TRUE~escolaridad_rec_original_9)) %>%
dplyr::mutate(escolaridad_rec_original_8=
dplyr::case_when(escolaridad_rec_original_1==last_esc & treat_per_usr>8 & !is.na(escolaridad_rec_original_1)~escolaridad_rec_original_1,
TRUE~escolaridad_rec_original_8)) %>%
dplyr::mutate(escolaridad_rec_original_7=
dplyr::case_when(escolaridad_rec_original_1==last_esc & treat_per_usr>7 & !is.na(escolaridad_rec_original_1)~escolaridad_rec_original_1,
TRUE~escolaridad_rec_original_7)) %>%
dplyr::mutate(escolaridad_rec_original_6=
dplyr::case_when(escolaridad_rec_original_1==last_esc & treat_per_usr>6 & !is.na(escolaridad_rec_original_1)~escolaridad_rec_original_1,
TRUE~escolaridad_rec_original_6)) %>%
dplyr::mutate(escolaridad_rec_original_5=
dplyr::case_when(escolaridad_rec_original_1==last_esc & treat_per_usr>5 & !is.na(escolaridad_rec_original_1)~escolaridad_rec_original_1,
TRUE~escolaridad_rec_original_5)) %>%
dplyr::mutate(escolaridad_rec_original_4=
dplyr::case_when(escolaridad_rec_original_1==last_esc & treat_per_usr>4 & !is.na(escolaridad_rec_original_1)~escolaridad_rec_original_1,
TRUE~escolaridad_rec_original_4)) %>%
dplyr::mutate(escolaridad_rec_original_3=
dplyr::case_when(escolaridad_rec_original_1==last_esc & treat_per_usr>3 & !is.na(escolaridad_rec_original_1)~escolaridad_rec_original_1,
TRUE~escolaridad_rec_original_3)) %>%
dplyr::mutate(escolaridad_rec_original_2=
dplyr::case_when(escolaridad_rec_original_1==last_esc & treat_per_usr>2 & !is.na(escolaridad_rec_original_1)~escolaridad_rec_original_1,
TRUE~escolaridad_rec_original_2)) %>%
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
#a1))cambiar valores vacíos intermedios /// fijarse en & escolaridad_rec_tot_cond==1
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
#reemplazar el número intermedio por cada tratamiento para cada usuario
dplyr::mutate(escolaridad_rec_original_9=dplyr::case_when(escolaridad_rec_original_8==escolaridad_rec_original_10 & is.na(escolaridad_rec_original_9)&!is.na(escolaridad_rec_original_10)~escolaridad_rec_original_10,TRUE~escolaridad_rec_original_9)) %>%
# dplyr::filter(!is.na(escolaridad_rec_original_10)) %>% View()
dplyr::mutate(escolaridad_rec_original_8=dplyr::case_when(escolaridad_rec_original_7==escolaridad_rec_original_9 & is.na(escolaridad_rec_original_8)&!is.na(escolaridad_rec_original_9)~escolaridad_rec_original_9,TRUE~escolaridad_rec_original_8)) %>%
# dplyr::filter(!is.na(escolaridad_rec_original_9)) %>% View()
dplyr::mutate(escolaridad_rec_original_7=dplyr::case_when(escolaridad_rec_original_6==escolaridad_rec_original_8 & is.na(escolaridad_rec_original_7)&!is.na(escolaridad_rec_original_8)~escolaridad_rec_original_8 ,TRUE~escolaridad_rec_original_7)) %>%
# dplyr::filter(!is.na(escolaridad_rec_original_8)) %>% View()
dplyr::mutate(escolaridad_rec_original_6=dplyr::case_when(escolaridad_rec_original_5==escolaridad_rec_original_7& is.na(escolaridad_rec_original_6)&!is.na(escolaridad_rec_original_7)~escolaridad_rec_original_7,TRUE~escolaridad_rec_original_6)) %>%
# dplyr::filter(!is.na(escolaridad_rec_original_7)) %>% View()
dplyr::mutate(escolaridad_rec_original_5=dplyr::case_when(escolaridad_rec_original_4==escolaridad_rec_original_6 & is.na(escolaridad_rec_original_5)&!is.na(escolaridad_rec_original_6)~escolaridad_rec_original_6,TRUE~escolaridad_rec_original_5)) %>%
# dplyr::filter(!is.na(escolaridad_rec_original_6)) %>% View()
dplyr::mutate(escolaridad_rec_original_4=dplyr::case_when(escolaridad_rec_original_3==escolaridad_rec_original_5 & is.na(escolaridad_rec_original_4)&!is.na(escolaridad_rec_original_5)~escolaridad_rec_original_5,TRUE~escolaridad_rec_original_4)) %>%
# dplyr::filter(!is.na(escolaridad_rec_original_5)) %>% View()
dplyr::mutate(escolaridad_rec_original_3=dplyr::case_when(escolaridad_rec_original_2==escolaridad_rec_original_4 & is.na(escolaridad_rec_original_3)&!is.na(escolaridad_rec_original_4)~escolaridad_rec_original_4,TRUE~escolaridad_rec_original_3)) %>%
# dplyr::filter(!is.na(escolaridad_rec_original_4)) %>% View()
dplyr::mutate(escolaridad_rec_original_2=dplyr::case_when(escolaridad_rec_original_1==escolaridad_rec_original_3 & is.na(escolaridad_rec_original_2)&!is.na(escolaridad_rec_original_3)~escolaridad_rec_original_3,TRUE~escolaridad_rec_original_2)) %>%
# dplyr::filter(!is.na(escolaridad_rec_original_3)) %>% View()
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
##a2))si tiene información en la segunda pero no en la primera, y no es un valor intermedio como secundaria completa (ya que en ese caso puede adoptar más de un valor: más o igual a ese valor), imputarlo
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
dplyr::mutate(escolaridad_rec_original_1=dplyr::case_when(escolaridad_rec_original_2==3~3,
escolaridad_rec_original_2==1~1,
TRUE~escolaridad_rec_original_1)) %>%
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
##a3))si hay más de 2 tratamientos por usuarios, y tiene información en la segunda pero no en la primera, y es un valor intermedio pero tiene un tercer tratamiento con el mismo valor, imputarlo
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
dplyr::mutate(escolaridad_rec_original_1=dplyr::case_when(escolaridad_rec_original_2==2 & escolaridad_rec_original_3==2~3,TRUE~escolaridad_rec_original_1)) %>%
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
#medidas para capturar inconsistencias a lo largo de todos los tratamientos de cada usuario
#escolaridad_rec_imputed4 %>% #escolaridad_rec_tot_cond
#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:#:
dplyr::mutate(across(c(escolaridad_rec_original_1:escolaridad_rec_original_10),~dplyr::case_when(.==1~1,TRUE~0), .names="1_more_high_{col}")) %>%
dplyr::mutate(across(c(escolaridad_rec_original_1:escolaridad_rec_original_10),~dplyr::case_when(.==2~1,TRUE~0), .names="2_high_{col}")) %>%
dplyr::mutate(across(c(escolaridad_rec_original_1:escolaridad_rec_original_10),~dplyr::case_when(.==3~1,TRUE~0), .names="3_primary_{col}")) %>%
dplyr::mutate(suma_vals_escolaridad_rec_1_more_high = base::rowSums(dplyr::select(., starts_with("1_more_high_")))) %>%
dplyr::mutate(suma_vals_escolaridad_rec_2_high = base::rowSums(dplyr::select(., starts_with("2_high_")))) %>%
dplyr::mutate(suma_vals_escolaridad_rec_3_primary = base::rowSums(dplyr::select(., starts_with("3_primary_"))))
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
#IMPUTACIONES
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
escolaridad_rec_imputed5<-
escolaridad_rec_imputed4 %>%
#hacer una suma de más NA's de los que debería tener según la cantidad de tratamientos que tiene la persona
#:#:#:#:#:#:#:#:#:
dplyr::mutate(sum_nas_esc_post=base::rowSums(is.na(dplyr::select(., starts_with("escolaridad_rec_original_")))))%>%
dplyr::mutate(escolaridad_rec_tot_nas_en_medio_post=dplyr::case_when(
(sum_nas_esc_post>10 & treat_per_usr==10)|
(sum_nas_esc_post>1 & treat_per_usr==9)|
(sum_nas_esc_post>2 & treat_per_usr==8)|
(sum_nas_esc_post>3 & treat_per_usr==7)|
(sum_nas_esc_post>4 & treat_per_usr==6)|
(sum_nas_esc_post>5 & treat_per_usr==5)|
(sum_nas_esc_post>6 & treat_per_usr==4)|
(sum_nas_esc_post>7 & treat_per_usr==3)|
(sum_nas_esc_post>8 & treat_per_usr==2)|
(sum_nas_esc_post>9 & treat_per_usr==1)~1,TRUE~0)) %>%
#dplyr::filter(escolaridad_rec_tot_nas_en_medio_post>0,treat_per_usr>1)
#d864967fa0b1c5bb1d4eb5f6a7c8c2c1
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
#b0))valor inicial y sólo un tratamiento, se imputa por el valor imputado más frecuente de las 30 bases de datos
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
dplyr::mutate(escolaridad_rec_original_1=dplyr::case_when(
is.na(escolaridad_rec_original_1) & treat_per_usr==1 &
(escolaridad_rec_3_primary_1>escolaridad_rec_2_high_1)&
(escolaridad_rec_2_high_1>escolaridad_rec_3_primary_1)~3,
is.na(escolaridad_rec_original_1) & treat_per_usr==1 &
(escolaridad_rec_2_high_1>escolaridad_rec_3_primary_1)&
(escolaridad_rec_2_high_1>escolaridad_rec_1_more_high_1)~2,
is.na(escolaridad_rec_original_1) & treat_per_usr==1 &
(escolaridad_rec_1_more_high_1>escolaridad_rec_3_primary_1)&
(escolaridad_rec_1_more_high_1>escolaridad_rec_2_high_1)~1,
TRUE~escolaridad_rec_original_1)) %>%
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
#b1))valor en el segundo tratamiento es intermedio, inicial se imputa, dependiendo si primaria es mayor que intermedio o no
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
###
#dplyr::filter(is.na(escolaridad_rec_original_1),!is.na(escolaridad_rec_original_2)) %>%
#dplyr::select(escolaridad_rec_original_1,escolaridad_rec_original_2,escolaridad_rec_3_primary_1,escolaridad_rec_2_high_1,escolaridad_rec_1_more_high_1) %>% View()
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#
dplyr::mutate(escolaridad_rec_original_1=dplyr::case_when(
is.na(escolaridad_rec_original_1) & escolaridad_rec_original_2==2 & (escolaridad_rec_3_primary_1>escolaridad_rec_2_high_1)~3,
is.na(escolaridad_rec_original_1) & escolaridad_rec_original_2==2 & (escolaridad_rec_3_primary_1<escolaridad_rec_2_high_1)~2,TRUE~escolaridad_rec_original_1))%>%
#dplyr::filter(escolaridad_rec_tot_nas_en_medio_post>0,treat_per_usr>1)
#610dd4dba4dbb62848691b6916828948
#90d581cd11064c41b82f8e4d6ff7b70b
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
#b2))Valor final es vacío, hay un valor anterior
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
dplyr::mutate(escolaridad_rec_original_10= dplyr::case_when(
#
#si la educación en el tratamiento anterior es la máxima, imputar con el mismo valor
treat_per_usr==10 & is.na(escolaridad_rec_original_10) & escolaridad_rec_original_9==1~1,
treat_per_usr==10 & is.na(escolaridad_rec_original_10) & escolaridad_rec_original_9==1~1,
#si la educación en el tratamiento anterior es intermedio, ver cuál es el valor más creible (conserva intermedio o logra universitario)
treat_per_usr==10 & is.na(escolaridad_rec_original_10) & escolaridad_rec_original_9==2 &
(escolaridad_rec_1_more_high_10>escolaridad_rec_2_high_10)~1,
treat_per_usr==10 & is.na(escolaridad_rec_original_10) & escolaridad_rec_original_9==2 &
(escolaridad_rec_1_more_high_10<escolaridad_rec_2_high_10)~2,
#si la educación en el tratamiento anterior es la más baja, ver cuál es el valor más creible (mantiene educación, logra intermedio o logra universitario)
treat_per_usr==10 & is.na(escolaridad_rec_original_10) & escolaridad_rec_original_9==3 &
(escolaridad_rec_1_more_high_10>escolaridad_rec_2_high_10) & (escolaridad_rec_1_more_high_10>escolaridad_rec_3_primary_10)~1,
treat_per_usr==10 & is.na(escolaridad_rec_original_10) & escolaridad_rec_original_9==3 &
(escolaridad_rec_2_high_10 >escolaridad_rec_1_more_high_10) & (escolaridad_rec_2_high_10>escolaridad_rec_3_primary_10)~2,
treat_per_usr==10 & is.na(escolaridad_rec_original_10) & escolaridad_rec_original_9==3 &
(escolaridad_rec_3_primary_10 >escolaridad_rec_2_high_10) & (escolaridad_rec_3_primary_10>escolaridad_rec_1_more_high_10)~2,TRUE~escolaridad_rec_original_10)) %>%
# dplyr::filter(escolaridad_rec_tot_nas_en_medio_post>0,treat_per_usr>1)
#
dplyr::mutate(escolaridad_rec_original_9= dplyr::case_when(
#si la educación en el tratamiento anterior es la máxima, imputar con el mismo valor
treat_per_usr==9 & is.na(escolaridad_rec_original_9) & escolaridad_rec_original_8==1~1,
treat_per_usr==9 & is.na(escolaridad_rec_original_9) & escolaridad_rec_original_8==1~1,
#si la educación en el tratamiento anterior es intermedio, ver cuál es el valor más creible (conserva intermedio o logra universitario)
treat_per_usr==9 & is.na(escolaridad_rec_original_9) & escolaridad_rec_original_8==2 &
(escolaridad_rec_1_more_high_9>escolaridad_rec_2_high_9)~1,
treat_per_usr==9 & is.na(escolaridad_rec_original_9) & escolaridad_rec_original_8==2 &
(escolaridad_rec_1_more_high_9<escolaridad_rec_2_high_9)~2,
#si la educación en el tratamiento anterior es la más baja, ver cuál es el valor más creible (mantiene educación, logra intermedio o logra universitario)
treat_per_usr==9 & is.na(escolaridad_rec_original_9) & escolaridad_rec_original_8==3 &
(escolaridad_rec_1_more_high_9>escolaridad_rec_2_high_9) & (escolaridad_rec_1_more_high_9>escolaridad_rec_3_primary_9)~1,
treat_per_usr==9 & is.na(escolaridad_rec_original_9) & escolaridad_rec_original_8==3 &
(escolaridad_rec_2_high_9 >escolaridad_rec_1_more_high_9) & (escolaridad_rec_2_high_9>escolaridad_rec_3_primary_9)~2,
treat_per_usr==9 & is.na(escolaridad_rec_original_9) & escolaridad_rec_original_8==3 &
(escolaridad_rec_3_primary_9 >escolaridad_rec_2_high_9) & (escolaridad_rec_3_primary_9>escolaridad_rec_1_more_high_9)~2,TRUE~escolaridad_rec_original_9)) %>%
#
dplyr::mutate(escolaridad_rec_original_8= dplyr::case_when(
#si la educación en el tratamiento anterior es la máxima, imputar con el mismo valor
treat_per_usr==8 & is.na(escolaridad_rec_original_8) & escolaridad_rec_original_7==1~1,
treat_per_usr==8 & is.na(escolaridad_rec_original_8) & escolaridad_rec_original_7==1~1,
#si la educación en el tratamiento anterior es intermedio, ver cuál es el valor más creible (conserva intermedio o logra universitario)
treat_per_usr==8 & is.na(escolaridad_rec_original_8) & escolaridad_rec_original_7==2 &
(escolaridad_rec_1_more_high_8>escolaridad_rec_2_high_8)~1,
treat_per_usr==8 & is.na(escolaridad_rec_original_8) & escolaridad_rec_original_7==2 &
(escolaridad_rec_1_more_high_8<escolaridad_rec_2_high_8)~2,
#si la educación en el tratamiento anterior es la más baja, ver cuál es el valor más creible (mantiene educación, logra intermedio o logra universitario)
treat_per_usr==8 & is.na(escolaridad_rec_original_8) & escolaridad_rec_original_7==3 &
(escolaridad_rec_1_more_high_8>escolaridad_rec_2_high_8) & (escolaridad_rec_1_more_high_8>escolaridad_rec_3_primary_8)~1,
treat_per_usr==8 & is.na(escolaridad_rec_original_8) & escolaridad_rec_original_7==3 &
(escolaridad_rec_2_high_8 >escolaridad_rec_1_more_high_8) & (escolaridad_rec_2_high_8>escolaridad_rec_3_primary_8)~2,
treat_per_usr==8 & is.na(escolaridad_rec_original_8) & escolaridad_rec_original_7==3 &
(escolaridad_rec_3_primary_8 >escolaridad_rec_2_high_8) & (escolaridad_rec_3_primary_8>escolaridad_rec_1_more_high_8)~2,TRUE~escolaridad_rec_original_8)) %>%
#
dplyr::mutate(escolaridad_rec_original_7= dplyr::case_when(
#si la educación en el tratamiento anterior es la máxima, imputar con el mismo valor
treat_per_usr==7 & is.na(escolaridad_rec_original_7) & escolaridad_rec_original_6==1~1,
treat_per_usr==7 & is.na(escolaridad_rec_original_7) & escolaridad_rec_original_6==1~1,
#si la educación en el tratamiento anterior es intermedio, ver cuál es el valor más creible (conserva intermedio o logra universitario)
treat_per_usr==7 & is.na(escolaridad_rec_original_7) & escolaridad_rec_original_6==2 &
(escolaridad_rec_1_more_high_7>escolaridad_rec_2_high_7)~1,
treat_per_usr==7 & is.na(escolaridad_rec_original_7) & escolaridad_rec_original_6==2 &
(escolaridad_rec_1_more_high_7<escolaridad_rec_2_high_7)~2,
#si la educación en el tratamiento anterior es la más baja, ver cuál es el valor más creible (mantiene educación, logra intermedio o logra universitario)
treat_per_usr==7 & is.na(escolaridad_rec_original_7) & escolaridad_rec_original_6==3 &
(escolaridad_rec_1_more_high_7>escolaridad_rec_2_high_7) & (escolaridad_rec_1_more_high_7>escolaridad_rec_3_primary_7)~1,
treat_per_usr==7 & is.na(escolaridad_rec_original_7) & escolaridad_rec_original_6==3 &
(escolaridad_rec_2_high_7 >escolaridad_rec_1_more_high_7) & (escolaridad_rec_2_high_7>escolaridad_rec_3_primary_7)~2,
treat_per_usr==7 & is.na(escolaridad_rec_original_7) & escolaridad_rec_original_6==3 &
(escolaridad_rec_3_primary_7 >escolaridad_rec_2_high_7) & (escolaridad_rec_3_primary_7>escolaridad_rec_1_more_high_7)~2,TRUE~escolaridad_rec_original_7)) %>%
#
dplyr::mutate(escolaridad_rec_original_6= dplyr::case_when(
#si la educación en el tratamiento anterior es la máxima, imputar con el mismo valor
treat_per_usr==6 & is.na(escolaridad_rec_original_6) & escolaridad_rec_original_5==1~1,
treat_per_usr==6 & is.na(escolaridad_rec_original_6) & escolaridad_rec_original_5==1~1,
#si la educación en el tratamiento anterior es intermedio, ver cuál es el valor más creible (conserva intermedio o logra universitario)
treat_per_usr==6 & is.na(escolaridad_rec_original_6) & escolaridad_rec_original_5==2 &
(escolaridad_rec_1_more_high_6>escolaridad_rec_2_high_6)~1,
treat_per_usr==6 & is.na(escolaridad_rec_original_6) & escolaridad_rec_original_5==2 &
(escolaridad_rec_1_more_high_6<escolaridad_rec_2_high_6)~2,
#si la educación en el tratamiento anterior es la más baja, ver cuál es el valor más creible (mantiene educación, logra intermedio o logra universitario)
treat_per_usr==6 & is.na(escolaridad_rec_original_6) & escolaridad_rec_original_5==3 &
(escolaridad_rec_1_more_high_6>escolaridad_rec_2_high_6) & (escolaridad_rec_1_more_high_6>escolaridad_rec_3_primary_6)~1,
treat_per_usr==6 & is.na(escolaridad_rec_original_6) & escolaridad_rec_original_5==3 &
(escolaridad_rec_2_high_6 >escolaridad_rec_1_more_high_6) & (escolaridad_rec_2_high_6>escolaridad_rec_3_primary_6)~2,
treat_per_usr==6 & is.na(escolaridad_rec_original_6) & escolaridad_rec_original_5==3 &
(escolaridad_rec_3_primary_6 >escolaridad_rec_2_high_6) & (escolaridad_rec_3_primary_6>escolaridad_rec_1_more_high_6)~2,TRUE~escolaridad_rec_original_6)) %>%
#
dplyr::mutate(escolaridad_rec_original_5= dplyr::case_when(
#si la educación en el tratamiento anterior es la máxima, imputar con el mismo valor
treat_per_usr==5 & is.na(escolaridad_rec_original_5) & escolaridad_rec_original_4==1~1,
treat_per_usr==5 & is.na(escolaridad_rec_original_5) & escolaridad_rec_original_4==1~1,
#si la educación en el tratamiento anterior es intermedio, ver cuál es el valor más creible (conserva intermedio o logra universitario)
treat_per_usr==5 & is.na(escolaridad_rec_original_5) & escolaridad_rec_original_4==2 &
(escolaridad_rec_1_more_high_5>escolaridad_rec_2_high_5)~1,
treat_per_usr==5 & is.na(escolaridad_rec_original_5) & escolaridad_rec_original_4==2 &
(escolaridad_rec_1_more_high_5<escolaridad_rec_2_high_5)~2,
#si la educación en el tratamiento anterior es la más baja, ver cuál es el valor más creible (mantiene educación, logra intermedio o logra universitario)
treat_per_usr==5 & is.na(escolaridad_rec_original_5) & escolaridad_rec_original_4==3 &
(escolaridad_rec_1_more_high_5>escolaridad_rec_2_high_5) & (escolaridad_rec_1_more_high_5>escolaridad_rec_3_primary_5)~1,
treat_per_usr==5 & is.na(escolaridad_rec_original_5) & escolaridad_rec_original_4==3 &
(escolaridad_rec_2_high_5 >escolaridad_rec_1_more_high_5) & (escolaridad_rec_2_high_5>escolaridad_rec_3_primary_5)~2,
treat_per_usr==5 & is.na(escolaridad_rec_original_5) & escolaridad_rec_original_4==3 &
(escolaridad_rec_3_primary_5 >escolaridad_rec_2_high_5) & (escolaridad_rec_3_primary_5>escolaridad_rec_1_more_high_5)~2,TRUE~escolaridad_rec_original_5)) %>%
#
dplyr::mutate(escolaridad_rec_original_4= dplyr::case_when(
#si la educación en el tratamiento anterior es la máxima, imputar con el mismo valor
treat_per_usr==4 & is.na(escolaridad_rec_original_4) & escolaridad_rec_original_3==1~1,
treat_per_usr==4 & is.na(escolaridad_rec_original_4) & escolaridad_rec_original_3==1~1,
#si la educación en el tratamiento anterior es intermedio, ver cuál es el valor más creible (conserva intermedio o logra universitario)
treat_per_usr==4 & is.na(escolaridad_rec_original_4) & escolaridad_rec_original_3==2 &
(escolaridad_rec_1_more_high_4>escolaridad_rec_2_high_4)~1,
treat_per_usr==4 & is.na(escolaridad_rec_original_4) & escolaridad_rec_original_3==2 &
(escolaridad_rec_1_more_high_4<escolaridad_rec_2_high_4)~2,
#si la educación en el tratamiento anterior es la más baja, ver cuál es el valor más creible (mantiene educación, logra intermedio o logra universitario)
treat_per_usr==4 & is.na(escolaridad_rec_original_4) & escolaridad_rec_original_3==3 &
(escolaridad_rec_1_more_high_4>escolaridad_rec_2_high_4) & (escolaridad_rec_1_more_high_4>escolaridad_rec_3_primary_4)~1,
treat_per_usr==4 & is.na(escolaridad_rec_original_4) & escolaridad_rec_original_3==3 &
(escolaridad_rec_2_high_4 >escolaridad_rec_1_more_high_4) & (escolaridad_rec_2_high_4>escolaridad_rec_3_primary_4)~2,
treat_per_usr==4 & is.na(escolaridad_rec_original_4) & escolaridad_rec_original_3==3 &
(escolaridad_rec_3_primary_4 >escolaridad_rec_2_high_4) & (escolaridad_rec_3_primary_4>escolaridad_rec_1_more_high_4)~2,TRUE~escolaridad_rec_original_4)) %>%
#
dplyr::mutate(escolaridad_rec_original_3= dplyr::case_when(
#si la educación en el tratamiento anterior es la máxima, imputar con el mismo valor
treat_per_usr==3 & is.na(escolaridad_rec_original_3) & escolaridad_rec_original_3==1~1,
treat_per_usr==3 & is.na(escolaridad_rec_original_3) & escolaridad_rec_original_3==1~1,
#si la educación en el tratamiento anterior es intermedio, ver cuál es el valor más creible (conserva intermedio o logra universitario)
treat_per_usr==3 & is.na(escolaridad_rec_original_3) & escolaridad_rec_original_3==2 &
(escolaridad_rec_1_more_high_3>escolaridad_rec_2_high_3)~1,
treat_per_usr==3 & is.na(escolaridad_rec_original_3) & escolaridad_rec_original_3==2 &
(escolaridad_rec_1_more_high_3<escolaridad_rec_2_high_3)~2,
#si la educación en el tratamiento anterior es la más baja, ver cuál es el valor más creible (mantiene educación, logra intermedio o logra universitario)
treat_per_usr==3 & is.na(escolaridad_rec_original_3) & escolaridad_rec_original_2==3 &
(escolaridad_rec_1_more_high_3>escolaridad_rec_2_high_3) & (escolaridad_rec_1_more_high_3>escolaridad_rec_3_primary_3)~1,
treat_per_usr==3 & is.na(escolaridad_rec_original_3) & escolaridad_rec_original_2==3 &
(escolaridad_rec_2_high_3 >escolaridad_rec_1_more_high_3) & (escolaridad_rec_2_high_3>escolaridad_rec_3_primary_3)~2,
treat_per_usr==3 & is.na(escolaridad_rec_original_3) & escolaridad_rec_original_2==3 &
(escolaridad_rec_3_primary_3 >escolaridad_rec_2_high_3) & (escolaridad_rec_3_primary_3>escolaridad_rec_1_more_high_3)~2,TRUE~escolaridad_rec_original_3))
#:#:#:#:
# dplyr::filter(escolaridad_rec_tot_nas_en_medio_post>0,treat_per_usr>1)
#:#:#:#:
#comprobar si en verdad calza:
#%>%dplyr::filter(hash_key=="ef4325cda7ddd92f6218bb910c3e0895") %>% dplyr::select(escolaridad_rec_original_1,escolaridad_rec_original_2,treat_per_usr,escolaridad_rec_3_primary_1,escolaridad_rec_2_high_1)
#610dd4dba4dbb62848691b6916828948
#90d581cd11064c41b82f8e4d6ff7b70b
#escolaridad_rec_imputed5 %>%
# dplyr::filter(escolaridad_rec_tot_nas_en_medio_post>0,treat_per_usr>1)%>%dplyr::filter(hash_key=="98d6644d995ea2c8777a683160728004") %>% dplyr::select(escolaridad_rec_original_3,escolaridad_rec_original_4,escolaridad_rec_original_4,treat_per_usr,escolaridad_rec_3_primary_4,escolaridad_rec_2_high_4,escolaridad_rec_1_more_high_4)
#98d6644d995ea2c8777a683160728004
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
#b2))Valor final es vacío, hay un valor anterior
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
escolaridad_rec_imputed6<-
escolaridad_rec_imputed5 %>%
#dplyr::filter(escolaridad_rec_tot_nas_en_medio_post>0,treat_per_usr>1)%>%dplyr::filter(hash_key=="98d6644d995ea2c8777a683160728004") %>% dplyr::select(escolaridad_rec_original_4,escolaridad_rec_original_4,treat_per_usr,escolaridad_rec_3_primary_4,escolaridad_rec_2_high_4,escolaridad_rec_1_more_high_3)
dplyr::select(hash_key,starts_with("escolaridad_rec_original_")) %>%
tidyr::pivot_longer(cols = starts_with("escolaridad_rec_original_"),
names_to = "rn",
names_prefix = "escolaridad_rec_original_") %>%
dplyr::filter(!is.na(value)) %>%
dplyr::mutate(hash_rn=paste0(hash_key,"_",rn)) %>%
dplyr::select(hash_rn,value)
#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:
#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:
CONS_C1_df_dup_SEP_2020_match_miss4<-
CONS_C1_df_dup_SEP_2020_match_miss3 %>%
dplyr::group_by(hash_key) %>%
dplyr::mutate(rn=row_number()) %>%
dplyr::ungroup() %>%
dplyr::mutate(hash_rn=paste0(hash_key,"_",rn)) %>%
dplyr::left_join(escolaridad_rec_imputed6, by=c("hash_rn")) %>%
dplyr::mutate(escolaridad_rec=dplyr::case_when(value==1~"1-More than high school",value==2~"2-Completed high school or less",value==3~"3-Completed primary school or less")) %>%
#
dplyr::arrange(hash_key,rn) %>%
#dplyr::mutate(escolaridad_rec=dplyr::case_when(is.na(escolaridad_rec)~value,TRUE~as.character(escolaridad_rec))) %>%
dplyr::mutate(escolaridad_rec=parse_factor(as.character(escolaridad_rec),levels=c('3-Completed primary school or less', '2-Completed high school or less', '1-More than high school'), ordered =F,trim_ws=T,include_na =F, locale=locale(encoding = "Latin1"))) %>%
dplyr::select(-value,-hash_rn) %>%
data.table()
#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:
#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:
paste("Check inconsistencies with posterior educational attainments (0= No inconsistencies):",CONS_C1_df_dup_SEP_2020_match_miss4 %>%
dplyr::arrange(hash_key,rn) %>%
dplyr::group_by(hash_key) %>%
dplyr::mutate(escolaridad_rec_num=as.numeric(substr(escolaridad_rec, 1, 1)),
sig_escolaridad_rec_num=lead(escolaridad_rec_num),
ant_escolaridad_rec_num=lag(escolaridad_rec_num)) %>%
dplyr::ungroup() %>%
dplyr::filter(escolaridad_rec_num>ant_escolaridad_rec_num) %>%
dplyr::select(hash_key,rn,fech_ing_num, escolaridad_rec, escolaridad_rec_num, sig_escolaridad_rec_num,ant_escolaridad_rec_num) %>%
nrow())## [1] "Check inconsistencies with posterior educational attainments (0= No inconsistencies): 0"We ended having 246 missing values in educational attainment (users=243) , because the imputed values did not fulfilled the requirements of a progression of the educational attainment (eg., a user could not respond to have completed secondary school, but then answer that he had completed primary school only), for example, due to ties in the imputed values or no imputed values.
Marital status
Additionally, we replaced missing values of the marital status (n=198). Since different marital status were not particularly more vulnerable between each other, we selected the most frequent imputed value among the different imputed databases.
# Ver distintos valores propuestos para estado conyugal
estado_conyugal_2_imputed<-
cbind.data.frame(amelia_fit$imputations$imp1$row,
amelia_fit$imputations$imp1$estado_conyugal_2,
amelia_fit$imputations$imp2$estado_conyugal_2,
amelia_fit$imputations$imp3$estado_conyugal_2,
amelia_fit$imputations$imp4$estado_conyugal_2,
amelia_fit$imputations$imp5$estado_conyugal_2,
amelia_fit$imputations$imp6$estado_conyugal_2,
amelia_fit$imputations$imp7$estado_conyugal_2,
amelia_fit$imputations$imp8$estado_conyugal_2,
amelia_fit$imputations$imp9$estado_conyugal_2,
amelia_fit$imputations$imp10$estado_conyugal_2,
amelia_fit$imputations$imp11$estado_conyugal_2,
amelia_fit$imputations$imp12$estado_conyugal_2,
amelia_fit$imputations$imp13$estado_conyugal_2,
amelia_fit$imputations$imp14$estado_conyugal_2,
amelia_fit$imputations$imp15$estado_conyugal_2,
amelia_fit$imputations$imp16$estado_conyugal_2,
amelia_fit$imputations$imp17$estado_conyugal_2,
amelia_fit$imputations$imp18$estado_conyugal_2,
amelia_fit$imputations$imp19$estado_conyugal_2,
amelia_fit$imputations$imp20$estado_conyugal_2,
amelia_fit$imputations$imp21$estado_conyugal_2,
amelia_fit$imputations$imp22$estado_conyugal_2,
amelia_fit$imputations$imp23$estado_conyugal_2,
amelia_fit$imputations$imp24$estado_conyugal_2,
amelia_fit$imputations$imp25$estado_conyugal_2,
amelia_fit$imputations$imp26$estado_conyugal_2,
amelia_fit$imputations$imp27$estado_conyugal_2,
amelia_fit$imputations$imp28$estado_conyugal_2,
amelia_fit$imputations$imp29$estado_conyugal_2,
amelia_fit$imputations$imp30$estado_conyugal_2
)
estado_conyugal_2_imputed<-
estado_conyugal_2_imputed %>%
data.frame() %>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.estado_conyugal_2:amelia_fit.imputations.imp30.estado_conyugal_2),~dplyr::case_when(grepl("Married/Shared living arrangements",as.character(.))~1,TRUE~0), .names="married_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.estado_conyugal_2:amelia_fit.imputations.imp30.estado_conyugal_2),~dplyr::case_when(grepl("Separated/Divorced",as.character(.))~1,TRUE~0), .names="sep_div_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.estado_conyugal_2:amelia_fit.imputations.imp30.estado_conyugal_2),~dplyr::case_when(grepl("Single",as.character(.))~1,TRUE~0), .names="singl_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.estado_conyugal_2:amelia_fit.imputations.imp30.estado_conyugal_2),~dplyr::case_when(grepl("Widower",as.character(.))~1,TRUE~0), .names="widow_{col}"))%>%
dplyr::mutate(estado_conyugal_2_married = base::rowSums(dplyr::select(., starts_with("married_"))))%>%
dplyr::mutate(estado_conyugal_2_sep_div = base::rowSums(dplyr::select(., starts_with("sep_div_"))))%>%
dplyr::mutate(estado_conyugal_2_singl = base::rowSums(dplyr::select(., starts_with("singl_"))))%>%
dplyr::mutate(estado_conyugal_2_wid = base::rowSums(dplyr::select(., starts_with("widow_"))))%>%
#dplyr::summarise(min_mar=max(sus_ini_mod_mvv_mar[sus_ini_mod_mvv_mar<30]),min_oh=max(sus_ini_mod_mvv_oh[sus_ini_mod_mvv_oh<30]),min_pb=max(sus_ini_mod_mvv_pb[sus_ini_mod_mvv_pb<30]),min_coc=max(sus_ini_mod_mvv_coc[sus_ini_mod_mvv_coc<30]),min_otr=max(sus_ini_mod_mvv_otr[sus_ini_mod_mvv_otr<30]))
dplyr::mutate(estado_conyugal_2_tot=dplyr::case_when(estado_conyugal_2_married>0~1,TRUE~0)) %>%
dplyr::mutate(estado_conyugal_2_tot=dplyr::case_when(estado_conyugal_2_sep_div>0~estado_conyugal_2_tot+1,TRUE~estado_conyugal_2_tot)) %>%
dplyr::mutate(estado_conyugal_2_tot=dplyr::case_when(estado_conyugal_2_singl>0~estado_conyugal_2_tot+1,TRUE~estado_conyugal_2_tot)) %>%
dplyr::mutate(estado_conyugal_2_tot=dplyr::case_when(estado_conyugal_2_wid>0~estado_conyugal_2_tot+1,TRUE~estado_conyugal_2_tot)) %>%
janitor::clean_names()
estado_conyugal_2_imputed_cat_est_cony<-
estado_conyugal_2_imputed %>%
tidyr::pivot_longer(c(estado_conyugal_2_married, estado_conyugal_2_sep_div, estado_conyugal_2_singl, estado_conyugal_2_wid), names_to = "cat_est_conyugal", values_to = "count") %>%
dplyr::group_by(amelia_fit_imputations_imp1_row) %>%
dplyr::mutate(estado_conyugal_2_imputed_max=max(count,na.rm=T)) %>%
dplyr::ungroup() %>%
dplyr::filter(estado_conyugal_2_imputed_max==count) %>%
dplyr::select(amelia_fit_imputations_imp1_row,cat_est_conyugal,count) %>%
dplyr::group_by(amelia_fit_imputations_imp1_row) %>%
dplyr::mutate(n_row=n()) %>%
dplyr::ungroup() %>%
dplyr::mutate(cat_est_conyugal=dplyr::case_when(n_row>1~NA_character_,
TRUE~cat_est_conyugal)) %>%
dplyr::distinct(amelia_fit_imputations_imp1_row,.keep_all = T)
estado_conyugal_2_imputed<-
estado_conyugal_2_imputed %>%
dplyr::left_join(estado_conyugal_2_imputed_cat_est_cony, by="amelia_fit_imputations_imp1_row") %>%
dplyr::mutate(cat_est_conyugal=dplyr::case_when(cat_est_conyugal=="estado_conyugal_2_married"~"Married/Shared living arrangements",cat_est_conyugal=="estado_conyugal_2_sep_div"~"Separated/Divorced",cat_est_conyugal=="estado_conyugal_2_singl"~"Single",cat_est_conyugal=="estado_conyugal_2_wid"~"Widower"
))%>%
janitor::clean_names()
#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:
CONS_C1_df_dup_SEP_2020_match_miss5<-
CONS_C1_df_dup_SEP_2020_match_miss4 %>%
dplyr::left_join(dplyr::select(estado_conyugal_2_imputed,amelia_fit_imputations_imp1_row,cat_est_conyugal), by=c("row"="amelia_fit_imputations_imp1_row")) %>%
dplyr::mutate(estado_conyugal_2=factor(dplyr::case_when(is.na(estado_conyugal_2)~as.character(cat_est_conyugal),TRUE~as.character(estado_conyugal_2)))) %>%
data.table()
no_calzaron_estado_cony<-
CONS_C1_df_dup_SEP_2020_match_miss5 %>% dplyr::filter(is.na(estado_conyugal_2)) %>% dplyr::distinct(hash_key) %>% unlist()
#CONS_C1_df_dup_SEP_2020_match_miss5 %>%
#dplyr::filter(hash_key %in% CONS_C1_df_dup_SEP_2020_match_miss5 %>% dplyr::filter(is.na(estado_conyugal_2)) %>% dplyr::distinct(hash_key) %>% unlist())We could not resolve Marital status in 13 cases due to ties in the most frequent values.
Region & Type of Center (Public)
We looked over possible imputations to region of the center (n=28) and type of the center (public or private) (n=28).
# Ver distintos valores propuestos para estado conyugal
#evaluacindelprocesoteraputico nombre_region tipo_centro_pub
#no hay información. debemos imputar
no_mostrar=0
if (no_mostrar==1){
tipo_centro_nombre_region_nas_nombre_region<-
CONS_C1_df_dup_SEP_2020 %>%
#dplyr::filter(row %in% unlist(unique(CONS_C1_df_dup_SEP_2020_match[,"row"]))) %>%
dplyr::filter(is.na(nombre_region)) %>%
janitor::tabyl(tipo_centro, nombre_region)
}
nombre_region_imputed<-
cbind.data.frame(amelia_fit$imputations$imp1$row,
amelia_fit$imputations$imp1$nombre_region,
amelia_fit$imputations$imp2$nombre_region,
amelia_fit$imputations$imp3$nombre_region,
amelia_fit$imputations$imp4$nombre_region,
amelia_fit$imputations$imp5$nombre_region,
amelia_fit$imputations$imp6$nombre_region,
amelia_fit$imputations$imp7$nombre_region,
amelia_fit$imputations$imp8$nombre_region,
amelia_fit$imputations$imp9$nombre_region,
amelia_fit$imputations$imp10$nombre_region,
amelia_fit$imputations$imp11$nombre_region,
amelia_fit$imputations$imp12$nombre_region,
amelia_fit$imputations$imp13$nombre_region,
amelia_fit$imputations$imp14$nombre_region,
amelia_fit$imputations$imp15$nombre_region,
amelia_fit$imputations$imp16$nombre_region,
amelia_fit$imputations$imp17$nombre_region,
amelia_fit$imputations$imp18$nombre_region,
amelia_fit$imputations$imp19$nombre_region,
amelia_fit$imputations$imp20$nombre_region,
amelia_fit$imputations$imp21$nombre_region,
amelia_fit$imputations$imp22$nombre_region,
amelia_fit$imputations$imp23$nombre_region,
amelia_fit$imputations$imp24$nombre_region,
amelia_fit$imputations$imp25$nombre_region,
amelia_fit$imputations$imp26$nombre_region,
amelia_fit$imputations$imp27$nombre_region,
amelia_fit$imputations$imp28$nombre_region,
amelia_fit$imputations$imp29$nombre_region,
amelia_fit$imputations$imp30$nombre_region
)
nombre_region_imputed<-
nombre_region_imputed %>%
data.frame() %>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.nombre_region:amelia_fit.imputations.imp30.nombre_region),~dplyr::case_when(grepl("Antofagasta",as.character(.))~1,TRUE~0), .names="reg_02_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.nombre_region:amelia_fit.imputations.imp30.nombre_region),~dplyr::case_when(grepl("Araucan",as.character(.))~1,TRUE~0), .names="reg_09_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.nombre_region:amelia_fit.imputations.imp30.nombre_region),~dplyr::case_when(grepl("Arica",as.character(.))~1,TRUE~0), .names="reg_15_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.nombre_region:amelia_fit.imputations.imp30.nombre_region),~dplyr::case_when(grepl("Atacama",as.character(.))~1,TRUE~0), .names="reg_03_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.nombre_region:amelia_fit.imputations.imp30.nombre_region),~dplyr::case_when(grepl("Ays",as.character(.))~1,TRUE~0), .names="reg_11_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.nombre_region:amelia_fit.imputations.imp30.nombre_region),~dplyr::case_when(grepl("Biob",as.character(.))~1,TRUE~0), .names="reg_08_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.nombre_region:amelia_fit.imputations.imp30.nombre_region),~dplyr::case_when(grepl("Coquimbo",as.character(.))~1,TRUE~0), .names="reg_04_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.nombre_region:amelia_fit.imputations.imp30.nombre_region),~dplyr::case_when(grepl("Los Lagos",as.character(.))~1,TRUE~0), .names="reg_10_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.nombre_region:amelia_fit.imputations.imp30.nombre_region),~dplyr::case_when(grepl("Los R",as.character(.))~1,TRUE~0), .names="reg_14_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.nombre_region:amelia_fit.imputations.imp30.nombre_region),~dplyr::case_when(grepl("Magallanes",as.character(.))~1,TRUE~0), .names="reg_12_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.nombre_region:amelia_fit.imputations.imp30.nombre_region),~dplyr::case_when(grepl("Maule",as.character(.))~1,TRUE~0), .names="reg_07_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.nombre_region:amelia_fit.imputations.imp30.nombre_region),~dplyr::case_when(grepl("Metropolitana",as.character(.))~1,TRUE~0), .names="reg_13_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.nombre_region:amelia_fit.imputations.imp30.nombre_region),~dplyr::case_when(grepl("uble",as.character(.))~1,TRUE~0), .names="reg_16_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.nombre_region:amelia_fit.imputations.imp30.nombre_region),~dplyr::case_when(grepl("Higgins",as.character(.))~1,TRUE~0), .names="reg_06_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.nombre_region:amelia_fit.imputations.imp30.nombre_region),~dplyr::case_when(grepl("Tarapac",as.character(.))~1,TRUE~0), .names="reg_01_{col}"))%>%
dplyr::mutate(across(c(amelia_fit.imputations.imp1.nombre_region:amelia_fit.imputations.imp30.nombre_region),~dplyr::case_when(grepl("Valpara",as.character(.))~1,TRUE~0), .names="reg_05_{col}"))%>%
dplyr::mutate(nombre_region_02 = base::rowSums(dplyr::select(., starts_with("reg_02_"))))%>%
dplyr::mutate(nombre_region_09 = base::rowSums(dplyr::select(., starts_with("reg_09_"))))%>%
dplyr::mutate(nombre_region_15 = base::rowSums(dplyr::select(., starts_with("reg_15_"))))%>%
dplyr::mutate(nombre_region_03 = base::rowSums(dplyr::select(., starts_with("reg_03_"))))%>%
dplyr::mutate(nombre_region_11 = base::rowSums(dplyr::select(., starts_with("reg_11_"))))%>%
dplyr::mutate(nombre_region_08 = base::rowSums(dplyr::select(., starts_with("reg_08_"))))%>%
dplyr::mutate(nombre_region_04 = base::rowSums(dplyr::select(., starts_with("reg_04_"))))%>%
dplyr::mutate(nombre_region_10 = base::rowSums(dplyr::select(., starts_with("reg_10_"))))%>%
dplyr::mutate(nombre_region_14 = base::rowSums(dplyr::select(., starts_with("reg_14_"))))%>%
dplyr::mutate(nombre_region_12 = base::rowSums(dplyr::select(., starts_with("reg_12_"))))%>%
dplyr::mutate(nombre_region_07 = base::rowSums(dplyr::select(., starts_with("reg_07_"))))%>%
dplyr::mutate(nombre_region_13 = base::rowSums(dplyr::select(., starts_with("reg_13_"))))%>%
dplyr::mutate(nombre_region_16 = base::rowSums(dplyr::select(., starts_with("reg_16_"))))%>%
dplyr::mutate(nombre_region_06 = base::rowSums(dplyr::select(., starts_with("reg_06_"))))%>%
dplyr::mutate(nombre_region_01 = base::rowSums(dplyr::select(., starts_with("reg_01_"))))%>%
dplyr::mutate(nombre_region_05 = base::rowSums(dplyr::select(., starts_with("reg_05_"))))%>%
#dplyr::summarise(min_mar=max(sus_ini_mod_mvv_mar[sus_ini_mod_mvv_mar<30]),min_oh=max(sus_ini_mod_mvv_oh[sus_ini_mod_mvv_oh<30]),min_pb=max(sus_ini_mod_mvv_pb[sus_ini_mod_mvv_pb<30]),min_coc=max(sus_ini_mod_mvv_coc[sus_ini_mod_mvv_coc<30]),min_otr=max(sus_ini_mod_mvv_otr[sus_ini_mod_mvv_otr<30]))
dplyr::mutate(nombre_region_tot=dplyr::case_when(nombre_region_02>0~1,TRUE~0)) %>%
dplyr::mutate(nombre_region_tot=dplyr::case_when(nombre_region_09>0~nombre_region_tot+1,TRUE~nombre_region_tot)) %>%
dplyr::mutate(nombre_region_tot=dplyr::case_when(nombre_region_15>0~nombre_region_tot+1,TRUE~nombre_region_tot)) %>%
dplyr::mutate(nombre_region_tot=dplyr::case_when(nombre_region_03>0~nombre_region_tot+1,TRUE~nombre_region_tot)) %>%
dplyr::mutate(nombre_region_tot=dplyr::case_when(nombre_region_11>0~nombre_region_tot+1,TRUE~nombre_region_tot)) %>%
dplyr::mutate(nombre_region_tot=dplyr::case_when(nombre_region_08>0~nombre_region_tot+1,TRUE~nombre_region_tot)) %>%
dplyr::mutate(nombre_region_tot=dplyr::case_when(nombre_region_04>0~nombre_region_tot+1,TRUE~nombre_region_tot)) %>%
dplyr::mutate(nombre_region_tot=dplyr::case_when(nombre_region_10>0~nombre_region_tot+1,TRUE~nombre_region_tot)) %>%
dplyr::mutate(nombre_region_tot=dplyr::case_when(nombre_region_14>0~nombre_region_tot+1,TRUE~nombre_region_tot)) %>%
dplyr::mutate(nombre_region_tot=dplyr::case_when(nombre_region_12>0~nombre_region_tot+1,TRUE~nombre_region_tot)) %>%
dplyr::mutate(nombre_region_tot=dplyr::case_when(nombre_region_07>0~nombre_region_tot+1,TRUE~nombre_region_tot)) %>%
dplyr::mutate(nombre_region_tot=dplyr::case_when(nombre_region_13>0~nombre_region_tot+1,TRUE~nombre_region_tot)) %>%
dplyr::mutate(nombre_region_tot=dplyr::case_when(nombre_region_16>0~nombre_region_tot+1,TRUE~nombre_region_tot)) %>%
dplyr::mutate(nombre_region_tot=dplyr::case_when(nombre_region_06>0~nombre_region_tot+1,TRUE~nombre_region_tot)) %>%
dplyr::mutate(nombre_region_tot=dplyr::case_when(nombre_region_01>0~nombre_region_tot+1,TRUE~nombre_region_tot)) %>%
dplyr::mutate(nombre_region_tot=dplyr::case_when(nombre_region_05>0~nombre_region_tot+1,TRUE~nombre_region_tot)) %>%
janitor::clean_names()
nombre_region_imputed_cat_reg<-
nombre_region_imputed %>%
tidyr::pivot_longer(c(nombre_region_01, nombre_region_02, nombre_region_03, nombre_region_04, nombre_region_05, nombre_region_06, nombre_region_07, nombre_region_08, nombre_region_09, nombre_region_10, nombre_region_11, nombre_region_12, nombre_region_13, nombre_region_14, nombre_region_15), names_to = "cat_nombre_region", values_to = "count") %>%
dplyr::group_by(amelia_fit_imputations_imp1_row) %>%
dplyr::mutate(nombre_region_imputed_max=max(count,na.rm=T)) %>%
dplyr::ungroup() %>%
dplyr::filter(nombre_region_imputed_max==count) %>%
dplyr::select(amelia_fit_imputations_imp1_row,cat_nombre_region,count) %>%
dplyr::group_by(amelia_fit_imputations_imp1_row) %>%
dplyr::mutate(n_row=n()) %>%
dplyr::ungroup() %>%
dplyr::mutate(cat_nombre_region=dplyr::case_when(n_row>1~NA_character_,
TRUE~cat_nombre_region)) %>%
dplyr::distinct(amelia_fit_imputations_imp1_row,.keep_all = T)
nombre_region_imputed<-
nombre_region_imputed %>%
dplyr::left_join(nombre_region_imputed_cat_reg, by="amelia_fit_imputations_imp1_row") %>%
dplyr::mutate(cat_nombre_region=dplyr::case_when(cat_nombre_region=="nombre_region_01"~"Tarapacá (01)",cat_nombre_region=="nombre_region_02"~"Antofagasta (02)",cat_nombre_region=="nombre_region_03"~"Atacama (03)",cat_nombre_region=="nombre_region_04"~"Coquimbo (04)",cat_nombre_region=="nombre_region_05"~"Valparaíso (05)",cat_nombre_region=="nombre_region_06"~"O'Higgins (06)",cat_nombre_region=="nombre_region_07"~"Maule (07)",cat_nombre_region=="nombre_region_08"~"Biobío (08)",cat_nombre_region=="nombre_region_09"~"Araucanía (09)",cat_nombre_region=="nombre_region_10"~"Los Lagos (10)",cat_nombre_region=="nombre_region_11"~"Aysén (11)",cat_nombre_region=="nombre_region_12"~"Magallanes (12)",cat_nombre_region=="nombre_region_13"~"Metropolitana (13)",
cat_nombre_region=="nombre_region_14"~"Los Ríos (14)",cat_nombre_region=="nombre_region_15"~"Arica (15)",cat_nombre_region=="nombre_region_16"~"Ñuble (16)",
))%>%
janitor::clean_names()
#_#_#_#_#_#_#_#_#_#_#_#_
#_#_#_#_#_#_#_#_#_#_#_#_
tipo_centro_pub_imputed<-
cbind.data.frame(amelia_fit$imputations$imp1$row,
amelia_fit$imputations$imp1$tipo_centro_pub,
amelia_fit$imputations$imp2$tipo_centro_pub,
amelia_fit$imputations$imp3$tipo_centro_pub,
amelia_fit$imputations$imp4$tipo_centro_pub,
amelia_fit$imputations$imp5$tipo_centro_pub,
amelia_fit$imputations$imp6$tipo_centro_pub,
amelia_fit$imputations$imp7$tipo_centro_pub,
amelia_fit$imputations$imp8$tipo_centro_pub,
amelia_fit$imputations$imp9$tipo_centro_pub,
amelia_fit$imputations$imp10$tipo_centro_pub,
amelia_fit$imputations$imp11$tipo_centro_pub,
amelia_fit$imputations$imp12$tipo_centro_pub,
amelia_fit$imputations$imp13$tipo_centro_pub,
amelia_fit$imputations$imp14$tipo_centro_pub,
amelia_fit$imputations$imp15$tipo_centro_pub,
amelia_fit$imputations$imp16$tipo_centro_pub,
amelia_fit$imputations$imp17$tipo_centro_pub,
amelia_fit$imputations$imp18$tipo_centro_pub,
amelia_fit$imputations$imp19$tipo_centro_pub,
amelia_fit$imputations$imp20$tipo_centro_pub,
amelia_fit$imputations$imp21$tipo_centro_pub,
amelia_fit$imputations$imp22$tipo_centro_pub,
amelia_fit$imputations$imp23$tipo_centro_pub,
amelia_fit$imputations$imp24$tipo_centro_pub,
amelia_fit$imputations$imp25$tipo_centro_pub,
amelia_fit$imputations$imp26$tipo_centro_pub,
amelia_fit$imputations$imp27$tipo_centro_pub,
amelia_fit$imputations$imp28$tipo_centro_pub,
amelia_fit$imputations$imp29$tipo_centro_pub,
amelia_fit$imputations$imp30$tipo_centro_pub
) %>%
melt(id.vars="amelia_fit$imputations$imp1$row") %>%
janitor::clean_names() %>%
dplyr::filter(value==TRUE) %>%
dplyr::group_by(amelia_fit_imputations_imp1_row) %>%
dplyr::summarise(tipo_centro_pub_to_imputation=ifelse(n()>15,1,0))
#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:
CONS_C1_df_dup_SEP_2020_match_miss6<-
CONS_C1_df_dup_SEP_2020_match_miss5 %>%
dplyr::left_join(dplyr::select(nombre_region_imputed,amelia_fit_imputations_imp1_row,cat_nombre_region), by=c("row"="amelia_fit_imputations_imp1_row")) %>%
dplyr::mutate(nombre_region=factor(dplyr::case_when(is.na(nombre_region)~as.character(cat_nombre_region),TRUE~as.character(nombre_region)))) %>%
dplyr::left_join(dplyr::select(tipo_centro_pub_imputed,amelia_fit_imputations_imp1_row,tipo_centro_pub_to_imputation), by=c("row"="amelia_fit_imputations_imp1_row")) %>%
dplyr::mutate(tipo_centro_pub=factor(dplyr::case_when(is.na(tipo_centro_pub)~as.logical(tipo_centro_pub_to_imputation),TRUE~as.logical(tipo_centro_pub)))) %>%
dplyr::select(-c(cat_est_conyugal,cat_nombre_region,tipo_centro_pub_to_imputation,tipo_centro_pub_to_imputation)) %>%
data.table()
#CONS_C1_df_dup_SEP_2020_match_miss6
#table(is.na(CONS_C1_df_dup_SEP_2020_match_miss6$tipo_centro_pub))
#table(is.na(CONS_C1_df_dup_SEP_2020_match_miss6$nombre_region))There were impossible to impute region of the center in 8 cases due to ties in the different imputed values. In case of public or private center, there were no missing values once imputed.
Diagnose of Drug Consumption
We looked over possible imputations to the diagnosis of drug consumption (n=1).
# Ver distintos valores propuestos para estado conyugal
#evaluacindelprocesoteraputico nombre_region tipo_centro_pub
dg_trs_cons_sus_or_imputed<-
cbind.data.frame(amelia_fit$imputations$imp1$row,
amelia_fit$imputations$imp1$dg_trs_cons_sus_or,
amelia_fit$imputations$imp2$dg_trs_cons_sus_or,
amelia_fit$imputations$imp3$dg_trs_cons_sus_or,
amelia_fit$imputations$imp4$dg_trs_cons_sus_or,
amelia_fit$imputations$imp5$dg_trs_cons_sus_or,
amelia_fit$imputations$imp6$dg_trs_cons_sus_or,
amelia_fit$imputations$imp7$dg_trs_cons_sus_or,
amelia_fit$imputations$imp8$dg_trs_cons_sus_or,
amelia_fit$imputations$imp9$dg_trs_cons_sus_or,
amelia_fit$imputations$imp10$dg_trs_cons_sus_or,
amelia_fit$imputations$imp11$dg_trs_cons_sus_or,
amelia_fit$imputations$imp12$dg_trs_cons_sus_or,
amelia_fit$imputations$imp13$dg_trs_cons_sus_or,
amelia_fit$imputations$imp14$dg_trs_cons_sus_or,
amelia_fit$imputations$imp15$dg_trs_cons_sus_or,
amelia_fit$imputations$imp16$dg_trs_cons_sus_or,
amelia_fit$imputations$imp17$dg_trs_cons_sus_or,
amelia_fit$imputations$imp18$dg_trs_cons_sus_or,
amelia_fit$imputations$imp19$dg_trs_cons_sus_or,
amelia_fit$imputations$imp20$dg_trs_cons_sus_or,
amelia_fit$imputations$imp21$dg_trs_cons_sus_or,
amelia_fit$imputations$imp22$dg_trs_cons_sus_or,
amelia_fit$imputations$imp23$dg_trs_cons_sus_or,
amelia_fit$imputations$imp24$dg_trs_cons_sus_or,
amelia_fit$imputations$imp25$dg_trs_cons_sus_or,
amelia_fit$imputations$imp26$dg_trs_cons_sus_or,
amelia_fit$imputations$imp27$dg_trs_cons_sus_or,
amelia_fit$imputations$imp28$dg_trs_cons_sus_or,
amelia_fit$imputations$imp29$dg_trs_cons_sus_or,
amelia_fit$imputations$imp30$dg_trs_cons_sus_or
) %>%
melt(id.vars="amelia_fit$imputations$imp1$row") %>%
janitor::clean_names() %>%
dplyr::filter(value==TRUE) %>%
dplyr::group_by(amelia_fit_imputations_imp1_row) %>%
dplyr::summarise(dg_trs_cons_imputation=ifelse(n()>15,1,0))
#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:
CONS_C1_df_dup_SEP_2020_match_miss7<-
CONS_C1_df_dup_SEP_2020_match_miss6 %>%
dplyr::left_join(dplyr::select(dg_trs_cons_sus_or_imputed,amelia_fit_imputations_imp1_row,dg_trs_cons_imputation), by=c("row"="amelia_fit_imputations_imp1_row")) %>%
dplyr::mutate(dg_trs_cons_sus_or=factor(dplyr::case_when(is.na(dg_trs_cons_sus_or)~as.logical(dg_trs_cons_imputation),TRUE~as.logical(dg_trs_cons_sus_or)))) %>%
dplyr::select(-dg_trs_cons_imputation) %>%
data.table()
#CONS_C1_df_dup_SEP_2020_match_miss6
#table(is.na(CONS_C1_df_dup_SEP_2020_match_miss6$tipo_centro_pub))
#table(is.na(CONS_C1_df_dup_SEP_2020_match_miss6$nombre_region))Evaluation of the Therapeutic Process
Another variable that is worth imputing is the Evalution of the Therapeutic Process at Dishcarge (n= 7,378). In case of ties, we selected the imputed values with the value with the minimum evaluation. Must consider that most of the null values could be explained by censoring or not completition of the treatment at the period of the study (7,361).
# Ver distintos valores propuestos para sustancia de inciio
evaluacindelprocesoteraputico_imputed<-
cbind.data.frame(amelia_fit$imputations$imp1$row,
amelia_fit$imputations$imp1$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp2$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp3$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp4$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp5$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp6$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp7$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp8$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp9$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp10$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp11$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp12$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp13$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp14$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp15$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp16$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp17$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp18$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp19$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp20$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp21$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp22$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp23$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp24$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp25$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp26$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp27$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp28$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp29$evaluacindelprocesoteraputico,
amelia_fit$imputations$imp30$evaluacindelprocesoteraputico
) %>%
melt(id.vars="amelia_fit$imputations$imp1$row") %>%
janitor::clean_names() %>%
dplyr::arrange(amelia_fit_imputations_imp1_row) %>%
dplyr::ungroup() %>%
dplyr::group_by(amelia_fit_imputations_imp1_row) %>%
dplyr::summarise(high_ach_1=sum(value == "1-High Achievement",na.rm=T),
med_ach_2=sum(value == "2-Medium Achievement",na.rm=T),
min_ach_3=sum(value =="3-Minimum Achievement",na.rm=T)) %>%
dplyr::ungroup() %>%
dplyr::left_join(dplyr::select(CONS_C1_df_dup_SEP_2020,row,motivodeegreso_mod_imp),by=c("amelia_fit_imputations_imp1_row"="row")) %>%
dplyr::mutate(evaluacindelprocesoteraputico_imputation= dplyr::case_when(
(high_ach_1 >med_ach_2) & (med_ach_2 >min_ach_3)~"1-High Achievement",
(med_ach_2>high_ach_1) & (med_ach_2 >min_ach_3)~"2-Medium Achievement",
(min_ach_3>med_ach_2) & (min_ach_3 >high_ach_1)~"3-Minimum Achievement"))
#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:
##
#CONS_C1_df_dup_SEP_2020 %>% janitor::tabyl(motivodeegreso_mod_imp,evaluacindelprocesoteraputico)
CONS_C1_df_dup_SEP_2020_match_miss8<-
CONS_C1_df_dup_SEP_2020_match_miss7 %>%
dplyr::left_join(evaluacindelprocesoteraputico_imputed[,c("amelia_fit_imputations_imp1_row","motivodeegreso_mod_imp","evaluacindelprocesoteraputico_imputation")], by=c("row"="amelia_fit_imputations_imp1_row")) %>%
dplyr::mutate(evaluacindelprocesoteraputico=factor(dplyr::case_when(is.na(evaluacindelprocesoteraputico) & motivodeegreso_mod_imp %in% c("Late Drop-out","Early Drop-out","Administrative discharge","Therapeutic discharge","Referral to another treatment")~evaluacindelprocesoteraputico_imputation,motivodeegreso_mod_imp=="Ongoing treatment"~NA_character_, TRUE~as.character(evaluacindelprocesoteraputico)))) %>%
dplyr::mutate(evaluacindelprocesoteraputico=parse_factor(as.character(evaluacindelprocesoteraputico),levels=c('1-High Achievement', '2-Medium Achievement','3-Minimum Achievement'), ordered =T,trim_ws=T,include_na =F, locale=locale(encoding = "UTF-8"))) %>%
dplyr::select(-evaluacindelprocesoteraputico_imputation) %>%
data.table()
CONS_C1_df_dup_SEP_2020_match_miss8 %>% janitor::tabyl(motivodeegreso_mod_imp,evaluacindelprocesoteraputico) %>%
knitr::kable(.,format = "html", format.args = list(decimal.mark = ".", big.mark = ","),
caption = paste0("Table 2. Cause of Discharge vs. Evaluation of the Therapeutic Procress"),
col.names = c("Cause of Discharge","1-High Achievement", "2- Medium Achievement","3- Minimum Achievement","Null Values"),
align =rep('c', 101)) %>%
kableExtra::kable_styling(bootstrap_options = c("striped", "hover"),font_size = 9) %>%
kableExtra::scroll_box(width = "100%", height = "375px") | Cause of Discharge | 1-High Achievement | 2- Medium Achievement | 3- Minimum Achievement | Null Values |
|---|---|---|---|---|
| Late Drop-out | 1,572 | 13,732 | 22,652 | 0 |
| Early Drop-out | 195 | 3,106 | 14,648 | 1 |
| Administrative discharge | 865 | 4,427 | 4,486 | 0 |
| Therapeutic discharge | 17,120 | 6,135 | 1,116 | 0 |
| Referral to another treatment | 1,298 | 5,833 | 4,703 | 0 |
| Ongoing treatment | 0 | 0 | 0 | 7,846 |
| Death | 0 | 0 | 1 | 0 |
| NA | 1 | 4 | 3 | 12 |
As seen in the table above, ongoing treatments did not have an evaluation process, which is logically valid, since their treatment competition was not captured.
Treatment Modality (Residential)
We looked over possible imputations to region of the center (n=97).
# Ver distintos valores propuestos para estado conyugal
#evaluacindelprocesoteraputico nombre_region tipo_centro_pub
tipo_de_plan_res_imputed<-
cbind.data.frame(amelia_fit$imputations$imp1$row,
amelia_fit$imputations$imp1$tipo_de_plan_res,
amelia_fit$imputations$imp2$tipo_de_plan_res,
amelia_fit$imputations$imp3$tipo_de_plan_res,
amelia_fit$imputations$imp4$tipo_de_plan_res,
amelia_fit$imputations$imp5$tipo_de_plan_res,
amelia_fit$imputations$imp6$tipo_de_plan_res,
amelia_fit$imputations$imp7$tipo_de_plan_res,
amelia_fit$imputations$imp8$tipo_de_plan_res,
amelia_fit$imputations$imp9$tipo_de_plan_res,
amelia_fit$imputations$imp10$tipo_de_plan_res,
amelia_fit$imputations$imp11$tipo_de_plan_res,
amelia_fit$imputations$imp12$tipo_de_plan_res,
amelia_fit$imputations$imp13$tipo_de_plan_res,
amelia_fit$imputations$imp14$tipo_de_plan_res,
amelia_fit$imputations$imp15$tipo_de_plan_res,
amelia_fit$imputations$imp16$tipo_de_plan_res,
amelia_fit$imputations$imp17$tipo_de_plan_res,
amelia_fit$imputations$imp18$tipo_de_plan_res,
amelia_fit$imputations$imp19$tipo_de_plan_res,
amelia_fit$imputations$imp20$tipo_de_plan_res,
amelia_fit$imputations$imp21$tipo_de_plan_res,
amelia_fit$imputations$imp22$tipo_de_plan_res,
amelia_fit$imputations$imp23$tipo_de_plan_res,
amelia_fit$imputations$imp24$tipo_de_plan_res,
amelia_fit$imputations$imp25$tipo_de_plan_res,
amelia_fit$imputations$imp26$tipo_de_plan_res,
amelia_fit$imputations$imp27$tipo_de_plan_res,
amelia_fit$imputations$imp28$tipo_de_plan_res,
amelia_fit$imputations$imp29$tipo_de_plan_res,
amelia_fit$imputations$imp30$tipo_de_plan_res
) %>%
melt(id.vars="amelia_fit$imputations$imp1$row") %>%
janitor::clean_names() %>%
dplyr::group_by(amelia_fit_imputations_imp1_row) %>%
dplyr::summarise(n_res=sum(value=="1",na.rm=T),n_amb=sum(value=="0",na.rm=T))
#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:#:#:#::#:#:#:
CONS_C1_df_dup_SEP_2020_match_miss9<-
CONS_C1_df_dup_SEP_2020_match_miss8 %>%
dplyr::left_join(dplyr::select(tipo_de_plan_res_imputed,amelia_fit_imputations_imp1_row,n_res,n_amb), by=c("row"="amelia_fit_imputations_imp1_row")) %>%
dplyr::mutate(tipo_de_plan_res=factor(dplyr::case_when(is.na(tipo_de_plan_res)& (n_res>n_amb)~"1",is.na(tipo_de_plan_res)& (n_res<n_amb)~"0",TRUE~as.character(tipo_de_plan_res)))) %>%
dplyr::select(-n_res,-n_amb) %>%
data.table()
#CONS_C1_df_dup_SEP_2020_match_miss6
#table(is.na(CONS_C1_df_dup_SEP_2020_match_miss6$tipo_centro_pub))
#table(is.na(CONS_C1_df_dup_SEP_2020_match_miss6$nombre_region))As a result of the process of imputation, some values were not possible to impute (n=5).
Sample Characteristics
We checked the characteristics of the sample depending on type of treatment (Residential or Outpatients).
#prop.table(table(CONS_C1_df_dup_SEP_2020_match$abandono_temprano_rec,CONS_C1_df_dup_SEP_2020_match$tipo_de_plan_res),2)
match.on_tot <- c("row", "hash_key","sus_ini_mod_mvv","estado_conyugal_2","escolaridad_rec","edad_ini_cons","freq_cons_sus_prin","origen_ingreso_mod","dg_cie_10_rec","nombre_region","tipo_centro_pub","abandono_temprano_rec","evaluacindelprocesoteraputico","dg_trs_cons_sus_or","tipo_de_plan_res","sexo_2","edad_al_ing","fech_ing_num")
#añado los imputados
CONS_C1_df_dup_SEP_2020_match_miss_after_imp<-
CONS_C1_df_dup_SEP_2020_match_miss %>%
dplyr::select(-sus_ini_mod_mvv,-estado_conyugal_2,-escolaridad_rec,-freq_cons_sus_prin,-via_adm_sus_prin_act,-edad_ini_cons,-nombre_region,-tipo_centro_pub,-dg_trs_cons_sus_or,-evaluacindelprocesoteraputico,-tipo_de_plan_res) %>%
dplyr::left_join(dplyr::select(CONS_C1_df_dup_SEP_2020_match_miss9,
row,
sus_ini_mod_mvv,
estado_conyugal_2,
escolaridad_rec,
freq_cons_sus_prin,
nombre_region,
tipo_centro_pub,
evaluacindelprocesoteraputico,
dg_trs_cons_sus_or,
tipo_de_plan_res,
edad_ini_cons,rn),by="row") %>%
dplyr::arrange(tipo_de_plan_res,hash_key,rn) %>%
#elimino esta variable porque es accesoria
dplyr::select(-edad_ini_sus_prin) %>%
dplyr::mutate(sum_miss = base::rowSums(is.na(dplyr::select(.,c("origen_ingreso_mod","dg_cie_10_rec","sexo_2","edad_al_ing","fech_ing_num","sus_ini_mod_mvv","tipo_centro_pub","estado_conyugal_2","escolaridad_rec","freq_cons_sus_prin","nombre_region","dg_trs_cons_sus_or","edad_ini_cons","tipo_de_plan_res"))))) %>%
dplyr::group_by(hash_key) %>%
dplyr::mutate(sum_miss=sum(sum_miss)) %>%
dplyr::ungroup()
CONS_C1_df_dup_SEP_2020_match_miss_after_imp_descartados <-
CONS_C1_df_dup_SEP_2020_match_miss_after_imp %>%
dplyr::filter(sum_miss>0)
CONS_C1_df_dup_SEP_2020_match_miss_after_imp_conservados <-
CONS_C1_df_dup_SEP_2020_match_miss_after_imp %>%
dplyr::filter(sum_miss==0) %>%
dplyr::select(-sum_miss) %>%
dplyr::left_join(CONS_C1_df_dup_SEP_2020[c("row","condicion_ocupacional_corr")], by="row")
# CONS_C1_df_dup_SEP_2020_match_miss_after_imp_conservados[complete.cases(CONS_C1_df_dup_SEP_2020_match_miss_after_imp_conservados[,..match.on_tot]),..match.on_tot] Considering that some missing values were not able to imputation (due to ties in the candidate values for imputation or inconsistent values for imputations) (335, users=275), we ended the process having 109,421 complete cases (users=84,773).
kableone <- function(x, ...) {
capture.output(x <- print(x,...))
knitr::kable(x,format= "html", format.args= list(decimal.mark= ".", big.mark= ","))
}
match.on.sel<-c("sus_ini_mod_mvv","estado_conyugal_2","escolaridad_rec","edad_ini_cons","freq_cons_sus_prin","origen_ingreso_mod","dg_cie_10_rec","nombre_region","dg_trs_cons_sus_or", "tipo_centro_pub","sexo_2","edad_al_ing","fech_ing_num","condicion_ocupacional_corr")
catVars<-
c("sus_ini_mod_mvv","estado_conyugal_2","escolaridad_rec","tipo_centro_pub","freq_cons_sus_prin","origen_ingreso_mod","dg_cie_10_rec","dg_trs_cons_sus_or","nombre_region","tipo_de_plan_res","sexo_2","condicion_ocupacional_corr")
#length(unique(CONS_C1_df_dup_SEP_2020_match$fech_ing_num))
#:#:#:#:#: DISMINUIR LA HETEROGENEIDAD DE LA FECHA DE INGRESO
# FORMAS DE CONSTREÑIR LA VARIABLE:
#CONS_C1_df_dup_SEP_2020_match$fech_ing_num<-round(CONS_C1_df_dup_SEP_2020_match$fech_ing_num/10,0)
#CONS_C1_df_dup_SEP_2020_match$fech_ing_num<-cut(CONS_C1_df_dup_SEP_2020_match$fech_ing_num,100)
#CONS_C1_df_dup_SEP_2020_match$fech_ing_num<-CONS_C1_df_dup_SEP_2020_match_fech_ing_num
#CONS_C1_df_dup_SEP_2020_match_fech_ing_num<-CONS_C1_df_dup_SEP_2020_match$fech_ing_num
#length(unique(round(CONS_C1_df_dup_SEP_2020_match$fech_ing_num,0)))
#length(unique(round(CONS_C1_df_dup_SEP_2020_match$fech_ing_num/10,0)))
#CONS_C1_df_dup_SEP_2020_match$fech_ing_num<-round(CONS_C1_df_dup_SEP_2020_match$fech_ing_num/10,0)
#:#:#:#:#:
paste0("Inconsistencies in dup vs. rn: ",CONS_C1_df_dup_SEP_2020_match_miss_after_imp_conservados%>%
dplyr::filter(dup!=rn) %>% nrow())## [1] "Inconsistencies in dup vs. rn: 0"CONS_C1_df_dup_SEP_2020_match_not_miss2 <-
CONS_C1_df_dup_SEP_2020_match_miss_after_imp_conservados %>%
dplyr::filter(dup==1) %>%
dplyr::select(-rn)
attr(CONS_C1_df_dup_SEP_2020_match_not_miss2$sus_ini_mod_mvv,"label")<-"Starting Substance"
attr(CONS_C1_df_dup_SEP_2020_match_not_miss2$estado_conyugal_2,"label")<-"Marital Status"
attr(CONS_C1_df_dup_SEP_2020_match_not_miss2$escolaridad_rec,"label")<-"Educational Attainment"
attr(CONS_C1_df_dup_SEP_2020_match_not_miss2$edad_ini_cons,"label")<-"Age of Onset of Drug Use"
attr(CONS_C1_df_dup_SEP_2020_match_not_miss2$freq_cons_sus_prin,"label")<-"Frequency of use of primary drug"
attr(CONS_C1_df_dup_SEP_2020_match_not_miss2$nombre_region,"label")<-"Region of the Center"
attr(CONS_C1_df_dup_SEP_2020_match_not_miss2$dg_cie_10_rec,"label")<-"Psychiatric Comorbidity"
attr(CONS_C1_df_dup_SEP_2020_match_not_miss2$dg_trs_cons_sus_or,"label")<-"Drug Dependence"
attr(CONS_C1_df_dup_SEP_2020_match_not_miss2$evaluacindelprocesoteraputico,"label")<-"Evaluation of the Therapeutic Process"
attr(CONS_C1_df_dup_SEP_2020_match_not_miss2$abandono_temprano_rec,"label")<-"Early Discharge"
attr(CONS_C1_df_dup_SEP_2020_match_not_miss2$tipo_de_plan_res,"label")<-"Residential"
attr(CONS_C1_df_dup_SEP_2020_match_not_miss2$tipo_centro_pub,"label")<-"Public Center"
attr(CONS_C1_df_dup_SEP_2020_match_not_miss2$condicion_ocupacional_corr,"label")<-"Occupational Status"
pre_tab1<-Sys.time()
tab1<-
CreateTableOne(vars = match.on.sel, strata = "tipo_de_plan_res",
data = CONS_C1_df_dup_SEP_2020_match_not_miss2, factorVars = catVars, smd=T)
post_tab1<-Sys.time()
diff_time_tab1=post_tab1-pre_tab1
kableone(tab1,
caption = paste0("Table 5. Covariate Balance in the Variables of Interest"),
col.names= c("Variables","Ambulatory","Residential", "p-values","test","SMD"),
nonnormal= c("edad_ini_cons","edad_al_ing","fech_ing_num"),#"\\hline",
smd=T, test=T, varLabels=T,noSpaces=T, printToggle=T, dropEqual=F) %>%
kableExtra::kable_styling(bootstrap_options = c("striped", "hover","condensed"),font_size= 10) %>%
#()
row_spec(1, bold = T, italic =T,color ="black",hline_after=T,extra_latex_after="\\arrayrulecolor{white}",font_size= 10) %>%
#footnote(general = "Here is a general comments of the table. ",
# number = c("Footnote 1; ", "Footnote 2; "),
# alphabet = c("Footnote A; ", "Footnote B; "),
# symbol = c("Footnote Symbol 1; ", "Footnote Symbol 2")
# )%>%
scroll_box(width = "100%", height = "400px") | 0 | 1 | p | test | SMD | |
|---|---|---|---|---|---|
| n | 72078 | 12695 | |||
| Starting Substance (%) | <0.001 | 0.369 | |||
| Alcohol | 41398 (57.4) | 5076 (40.0) | |||
| Cocaine hydrochloride | 2928 (4.1) | 514 (4.0) | |||
| Cocaine paste | 7676 (10.6) | 2230 (17.6) | |||
| Marijuana | 18414 (25.5) | 4557 (35.9) | |||
| Other | 1662 (2.3) | 318 (2.5) | |||
| Marital Status (%) | <0.001 | 0.310 | |||
| Married/Shared living arrangements | 26167 (36.3) | 2908 (22.9) | |||
| Separated/Divorced | 7712 (10.7) | 1315 (10.4) | |||
| Single | 37335 (51.8) | 8340 (65.7) | |||
| Widower | 864 (1.2) | 132 (1.0) | |||
| Educational Attainment (%) | <0.001 | 0.124 | |||
| 3-Completed primary school or less | 21855 (30.3) | 4573 (36.0) | |||
| 2-Completed high school or less | 37206 (51.6) | 6135 (48.3) | |||
| 1-More than high school | 13017 (18.1) | 1987 (15.7) | |||
| Age of Onset of Drug Use (median [IQR]) | 15.00 [14.00, 18.00] | 15.00 [13.00, 17.00] | <0.001 | nonnorm | 0.092 |
| Frequency of use of primary drug (%) | <0.001 | 0.767 | |||
| 1 day a week or more | 5322 (7.4) | 272 (2.1) | |||
| 2 to 3 days a week | 22316 (31.0) | 1327 (10.5) | |||
| 4 to 6 days a week | 12221 (17.0) | 1648 (13.0) | |||
| Daily | 28267 (39.2) | 9231 (72.7) | |||
| Did not use | 1096 (1.5) | 84 (0.7) | |||
| Less than 1 day a week | 2856 (4.0) | 133 (1.0) | |||
| Origen de Ingreso (Primera Entrada)/Motive of Admission to Treatment (First Entry) (%) | <0.001 | 0.509 | |||
| Spontaneous | 33640 (46.7) | 4277 (33.7) | |||
| Assisted Referral | 4936 (6.8) | 3004 (23.7) | |||
| Other | 3750 (5.2) | 739 (5.8) | |||
| Justice Sector | 7138 (9.9) | 811 (6.4) | |||
| Health Sector | 22614 (31.4) | 3864 (30.4) | |||
| Psychiatric Comorbidity (%) | <0.001 | 0.318 | |||
| Without psychiatric comorbidity | 29016 (40.3) | 3244 (25.6) | |||
| Diagnosis unknown (under study) | 13261 (18.4) | 2767 (21.8) | |||
| With psychiatric comorbidity | 29801 (41.3) | 6684 (52.7) | |||
| Region of the Center (%) | <0.001 | 0.388 | |||
| Antofagasta (02) | 2291 (3.2) | 697 (5.5) | |||
| Araucanía (09) | 2220 (3.1) | 161 (1.3) | |||
| Arica (15) | 1314 (1.8) | 729 (5.7) | |||
| Atacama (03) | 1831 (2.5) | 258 (2.0) | |||
| Aysén (11) | 798 (1.1) | 42 (0.3) | |||
| Biobío (08) | 5090 (7.1) | 702 (5.5) | |||
| Coquimbo (04) | 2798 (3.9) | 269 (2.1) | |||
| Los Lagos (10) | 2649 (3.7) | 375 (3.0) | |||
| Los Ríos (14) | 1112 (1.5) | 185 (1.5) | |||
| Magallanes (12) | 929 (1.3) | 31 (0.2) | |||
| Maule (07) | 4206 (5.8) | 642 (5.1) | |||
| Metropolitana (13) | 35962 (49.9) | 6251 (49.2) | |||
| Ñuble (16) | 540 (0.7) | 20 (0.2) | |||
| O’Higgins (06) | 3637 (5.0) | 573 (4.5) | |||
| Tarapacá (01) | 1348 (1.9) | 596 (4.7) | |||
| Valparaíso (05) | 5353 (7.4) | 1164 (9.2) | |||
| Drug Dependence = TRUE (%) | 50003 (69.4) | 11650 (91.8) | <0.001 | 0.590 | |
| Public Center = TRUE (%) | 57111 (79.2) | 3616 (28.5) | <0.001 | 1.183 | |
| Sexo Usuario/Sex of User = Women (%) | 17394 (24.1) | 3935 (31.0) | <0.001 | 0.154 | |
| Edad a la Fecha de Ingreso a Tratamiento (numérico continuo) (Primera Entrada)/Age at Admission to Treatment (First Entry) (median [IQR]) | 34.43 [27.55, 43.46] | 32.63 [26.34, 40.86] | <0.001 | nonnorm | 0.185 |
| Fecha de Ingreso a Tratamiento (Numérico)(c)/Date of Admission to Treatment (Numeric)(c) (median [IQR]) | 16577.00 [15730.00, 17359.00] | 16154.00 [15342.00, 17023.00] | <0.001 | nonnorm | 0.292 |
| Occupational Status (%) | <0.001 | 1.026 | |||
| Employed | 39517 (54.8) | 1770 (13.9) | |||
| Inactive | 7679 (10.7) | 1191 (9.4) | |||
| Looking for a job for the first time | 172 (0.2) | 20 (0.2) | |||
| No activity | 2664 (3.7) | 1819 (14.3) | |||
| Not seeking for work | 490 (0.7) | 337 (2.7) | |||
| Unemployed | 21556 (29.9) | 7558 (59.5) |
#"tipo_de_plan_ambulatorio",
#https://cran.r-project.org/web/packages/tableone/vignettes/smd.html
#http://rstudio-pubs-static.s3.amazonaws.com/405765_2ce448f9bde24148a5f94c535a34b70e.html
#https://cran.r-project.org/web/packages/tableone/vignettes/introduction.html
#https://cran.r-project.org/web/packages/tableone/tableone.pdf
#https://www.rdocumentation.org/packages/tableone/versions/0.12.0/topics/CreateTableOne
## Construct a table
#standardized mean differences of greater than 0.1We checked the similarity in the samples using other measures, such as the variance ratio of the samples and Kolmogorov-Smirnov(KS) statistics.
library(cobalt)
bal2<-bal.tab(CONS_C1_df_dup_SEP_2020_match_not_miss2[,match.on.sel], treat = CONS_C1_df_dup_SEP_2020_match_not_miss2$tipo_de_plan_res,
thresholds = c(m = .1, v = 2),
binary = "std",
continuous = "std",
stats = c("mean.diffs", "variance.ratios","ks.statistics"))
#"mean.diffs", "variance.ratios","ks.statistics","ovl.coefficient"
options(knitr.kable.NA = '')
bal2$Balance[,2]<-round(bal2$Balance[,2],2)
bal2$Balance[,4]<-round(bal2$Balance[,4],2)
bal2$Balance[,6]<-round(bal2$Balance[,6],2)
var_names<-
list("origen_ingreso_mod_Spontaneous"="Motive Admission-Spontaneous",
"origen_ingreso_mod_Assisted Referral"= "Motive Admission-Assisted Referral",
"origen_ingreso_mod_Other"="Motive Admission-Other",
"origen_ingreso_mod_Justice Sector"= "Motive Admission-Justice Sector",
"origen_ingreso_mod_Health Sector"="Motive Admission-Health Sector",
"dg_cie_10_rec_Without psychiatric comorbidity"="ICD-10-Wo/Psych Comorbidity",
"dg_cie_10_rec_Diagnosis unknown (under study)"="ICD-10-Dg. Unknown/under study",
"dg_cie_10_rec_With psychiatric comorbidity"="ICD-10-W/Psych Comorbidity",
"sexo_2_Women"="Sex-Women",
"edad_al_ing"="Age at Admission",
"fech_ing_num"="Date of Admission",
"duplicates_filtered"="Treatments (#)",
"more_one_treat"=">1 treatment",
"sus_ini_mod_mvv_Alcohol"= "Starting Substance-Alcohol",
"sus_ini_mod_mvv_Cocaine hydrochloride"= "Starting Substance-Cocaine hydrochloride",
"sus_ini_mod_mvv_Cocaine paste"="Starting Substance-Cocaine paste",
"sus_ini_mod_mvv_Marijuana"="Starting Substance-Marijuana",
"sus_ini_mod_mvv_Other"="Starting Substance-Other",
"estado_conyugal_2_Married/Shared living arrangements"="Marital Status-Married/Shared liv. arr.",
"condicion_ocupacional_corr_Employed"="Occ.Status-Employed",
"condicion_ocupacional_corr_Inactive"="Occ.Status-Inactive",
"condicion_ocupacional_corr_Looking for a job for the first time"="Occ.Status-Looking 1st job",
"condicion_ocupacional_corr_No activity"="Occ.Status- No activity",
"condicion_ocupacional_corr_Not seeking for work"="Occ.Status- Not seeking work",
"condicion_ocupacional_corr_Unemployed"="Occ.Status- Unemployed",
"estado_conyugal_2_Separated/Divorced"="Marital Status-Separated/Divorced",
"estado_conyugal_2_Single"= "Marital Status-Single",
"estado_conyugal_2_Widower"="Marital Status-Widower",
"escolaridad_rec_3-Completed primary school or less"="Educational Attainment-PS or less",
"escolaridad_rec_2-Completed high school or less"="Educational Attainment-HS or less",
"escolaridad_rec_1-More than high school"="Educational Attainment-More than HS",
"freq_cons_sus_prin_1 day a week or more"="Freq Drug Cons-1d/wk or more",
"freq_cons_sus_prin_2 to 3 days a week"="Freq Drug Cons-2-3d/wk",
"freq_cons_sus_prin_4 to 6 days a week"="Freq Drug Cons-4-6d/wk",
"freq_cons_sus_prin_Daily"="Freq Drug Cons-Daily",
"freq_cons_sus_prin_Did not use"="Freq Drug Cons-Did not use",
"freq_cons_sus_prin_Less than 1 day a week"="Freq Drug Cons-Less 1d/wk",
"nombre_region_Antofagasta (02)"="Region-Antofagasta(02)",
"nombre_region_Araucanía (09)"="Region-Araucanía(09)",
"nombre_region_Arica (15)"="Region-Arica(15)",
"nombre_region_Atacama (03)"="Region-Atacama(03)",
"nombre_region_Aysén (11)"="Region-Aysén(11)",
"nombre_region_Biobío (08)"="Region- Biobío(08)",
"nombre_region_Coquimbo (04)"="Region-Coquimbo(04)",
"nombre_region_Los Lagos (10)"="Region-Los Lagos(10)",
"nombre_region_Los Ríos (14)"="Region-Los Ríos(14)",
"nombre_region_Magallanes (12)"="Region-Magallanes(12)",
"nombre_region_Maule (07)"="Region-Maule(07)",
"nombre_region_Metropolitana (13)"="Region-Metropolitana(13)",
"nombre_region_Ñuble (16)"="Region-Ñuble(16)",
"nombre_region_O'Higgins (06)"="Region-O'Higgins(06)",
"nombre_region_Tarapacá (01)"="Region-Tarapacá(01)",
"nombre_region_Valparaíso (05)"="Region-Valparaíso(05)",
"tipo_centro_pub"="Public Center",
"dg_trs_cons_sus_or"= "Drug Dependence",
"edad_ini_cons"="Age of Onset of Drug Use",
"rn"="Treatment")
var.names<-data.table(data.frame(unlist(var_names)),keep.rownames = T) %>% janitor::clean_names()
balance_prev<-
data.table::data.table(bal2$Balance[,1:6],keep.rownames = T) %>%
dplyr::arrange(-abs(Diff.Un)) %>%
dplyr::left_join(var.names,by="rn") %>%
dplyr::select(unlist_var_names,everything()) %>%
dplyr::select(-rn)
balance_prev %>% #data.table::data.table(keep.rownames = F)
knitr::kable(.,format = "html", format.args = list(decimal.mark = ".", big.mark = ","),
caption = paste0("Table 4. Covariate Balance in the Variables of Interest"),
col.names = c("Variables","Nature of Variables", "Unadjusted SMDs","Threshold","Unadjusted Variance Ratios","Threshold","Unadjusted KS"),
align =rep('c', 101)) %>%
kableExtra::kable_styling(bootstrap_options = c("striped", "hover"),font_size = 10) %>%
kableExtra::add_footnote( c(paste("Note. ")),
notation = "none") %>%
kableExtra::scroll_box(width = "100%", height = "375px")| Variables | Nature of Variables | Unadjusted SMDs | Threshold | Unadjusted Variance Ratios | Threshold | Unadjusted KS |
|---|---|---|---|---|---|---|
| Public Center | Binary | -1.18 | Not Balanced, >0.1 | 0.51 | ||
| Occ.Status-Employed | Binary | -0.95 | Not Balanced, >0.1 | 0.41 | ||
| Freq Drug Cons-Daily | Binary | 0.72 | Not Balanced, >0.1 | 0.33 | ||
| Occ.Status- Unemployed | Binary | 0.62 | Not Balanced, >0.1 | 0.30 | ||
| Drug Dependence | Binary | 0.59 | Not Balanced, >0.1 | 0.22 | ||
| Freq Drug Cons-2-3d/wk | Binary | -0.52 | Not Balanced, >0.1 | 0.21 | ||
| Motive Admission-Assisted Referral | Binary | 0.48 | Not Balanced, >0.1 | 0.17 | ||
| Occ.Status- No activity | Binary | 0.38 | Not Balanced, >0.1 | 0.11 | ||
| Starting Substance-Alcohol | Binary | -0.35 | Not Balanced, >0.1 | 0.17 | ||
| ICD-10-Wo/Psych Comorbidity | Binary | -0.32 | Not Balanced, >0.1 | 0.15 | ||
| Marital Status-Married/Shared liv. arr. | Binary | -0.30 | Not Balanced, >0.1 | 0.13 | ||
| Marital Status-Single | Binary | 0.29 | Not Balanced, >0.1 | 0.14 | ||
| Date of Admission | Contin. | -0.29 | Not Balanced, >0.1 | 1.00 | Balanced, <2 | 0.14 |
| Motive Admission-Spontaneous | Binary | -0.27 | Not Balanced, >0.1 | 0.13 | ||
| Freq Drug Cons-1d/wk or more | Binary | -0.25 | Not Balanced, >0.1 | 0.05 | ||
| Starting Substance-Marijuana | Binary | 0.23 | Not Balanced, >0.1 | 0.10 | ||
| ICD-10-W/Psych Comorbidity | Binary | 0.23 | Not Balanced, >0.1 | 0.11 | ||
| Region-Arica(15) | Binary | 0.21 | Not Balanced, >0.1 | 0.04 | ||
| Starting Substance-Cocaine paste | Binary | 0.20 | Not Balanced, >0.1 | 0.07 | ||
| Freq Drug Cons-Less 1d/wk | Binary | -0.19 | Not Balanced, >0.1 | 0.03 | ||
| Age at Admission | Contin. | -0.19 | Not Balanced, >0.1 | 0.84 | Balanced, <2 | 0.07 |
| Region-Tarapacá(01) | Binary | 0.16 | Not Balanced, >0.1 | 0.03 | ||
| Sex-Women | Binary | 0.15 | Not Balanced, >0.1 | 0.07 | ||
| Occ.Status- Not seeking work | Binary | 0.15 | Not Balanced, >0.1 | 0.02 | ||
| Motive Admission-Justice Sector | Binary | -0.13 | Not Balanced, >0.1 | 0.04 | ||
| Educational Attainment-PS or less | Binary | 0.12 | Not Balanced, >0.1 | 0.06 | ||
| Region-Araucanía(09) | Binary | -0.12 | Not Balanced, >0.1 | 0.02 | ||
| Region-Magallanes(12) | Binary | -0.12 | Not Balanced, >0.1 | 0.01 | ||
| Freq Drug Cons-4-6d/wk | Binary | -0.11 | Not Balanced, >0.1 | 0.04 | ||
| Region-Antofagasta(02) | Binary | 0.11 | Not Balanced, >0.1 | 0.02 | ||
| Region-Coquimbo(04) | Binary | -0.10 | Not Balanced, >0.1 | 0.02 | ||
| Age of Onset of Drug Use | Contin. | -0.09 | Balanced, <0.1 | 0.91 | Balanced, <2 | 0.07 |
| Region-Aysén(11) | Binary | -0.09 | Balanced, <0.1 | 0.01 | ||
| Region-Ñuble(16) | Binary | -0.09 | Balanced, <0.1 | 0.01 | ||
| Freq Drug Cons-Did not use | Binary | -0.08 | Balanced, <0.1 | 0.01 | ||
| ICD-10-Dg. Unknown/under study | Binary | 0.08 | Balanced, <0.1 | 0.03 | ||
| Educational Attainment-HS or less | Binary | -0.07 | Balanced, <0.1 | 0.03 | ||
| Educational Attainment-More than HS | Binary | -0.06 | Balanced, <0.1 | 0.02 | ||
| Region- Biobío(08) | Binary | -0.06 | Balanced, <0.1 | 0.02 | ||
| Region-Valparaíso(05) | Binary | 0.06 | Balanced, <0.1 | 0.02 | ||
| Region-Los Lagos(10) | Binary | -0.04 | Balanced, <0.1 | 0.01 | ||
| Occ.Status-Inactive | Binary | -0.04 | Balanced, <0.1 | 0.01 | ||
| Motive Admission-Other | Binary | 0.03 | Balanced, <0.1 | 0.01 | ||
| Region-Atacama(03) | Binary | -0.03 | Balanced, <0.1 | 0.01 | ||
| Region-Maule(07) | Binary | -0.03 | Balanced, <0.1 | 0.01 | ||
| Marital Status-Widower | Binary | -0.02 | Balanced, <0.1 | 0.00 | ||
| Motive Admission-Health Sector | Binary | -0.02 | Balanced, <0.1 | 0.01 | ||
| Region-O’Higgins(06) | Binary | -0.02 | Balanced, <0.1 | 0.01 | ||
| Occ.Status-Looking 1st job | Binary | -0.02 | Balanced, <0.1 | 0.00 | ||
| Starting Substance-Other | Binary | 0.01 | Balanced, <0.1 | 0.00 | ||
| Marital Status-Separated/Divorced | Binary | -0.01 | Balanced, <0.1 | 0.00 | ||
| Region-Los Ríos(14) | Binary | -0.01 | Balanced, <0.1 | 0.00 | ||
| Region-Metropolitana(13) | Binary | -0.01 | Balanced, <0.1 | 0.01 | ||
| Starting Substance-Cocaine hydrochloride | Binary | 0.00 | Balanced, <0.1 | 0.00 | ||
| Note. |
We generated a plot to focus on unbalanced data.
Figure 8. Covariates Balance on Different Values
Specification
First, we had to discretize categorical variables into logical parameters, and for continuous covariates, we divide them into 20 equal parts.
catVars<-
c("sus_ini_mod_mvv","estado_conyugal_2","escolaridad_rec","tipo_centro_pub","freq_cons_sus_prin","origen_ingreso_mod","dg_cie_10_rec","dg_trs_cons_sus_or","nombre_region","tipo_de_plan_res","sexo_2","condicion_ocupacional_corr")
columna_dummy <- function(df, columna) {
df %>%
mutate_at(columna, ~paste(columna, eval(as.symbol(columna)), sep = "_")) %>%
mutate(valor = 1) %>%
spread(key = columna, value = valor, fill = 0)
}
quantiles = function(covar, n_q) {
p_q = seq(0, 1, 1/n_q)
val_q = quantile(covar, probs = p_q, na.rm = TRUE)
covar_out = rep(NA, length(covar))
for (i in 1:n_q) {
if (i==1) {covar_out[covar<val_q[i+1]] = i}
if (i>1 & i<n_q) {covar_out[covar>=val_q[i] & covar<val_q[i+1]] = i}
if (i==n_q) {covar_out[covar>=val_q[i] & covar<=val_q[i+1]] = i}}
covar_out
}
CONS_C1_df_dup_SEP_2020_match_not_miss3<-CONS_C1_df_dup_SEP_2020_match_not_miss2
for (i in c(1:length(catVars))){#catVars[-10] excluding treatment indicator
cat<-as.character(catVars[i])#catVars[-10] excluding treatment indicator
CONS_C1_df_dup_SEP_2020_match_not_miss3<-columna_dummy(CONS_C1_df_dup_SEP_2020_match_not_miss3,cat)
}
CONS_C1_df_dup_SEP_2020_match_not_miss3$tipo_de_plan_res_FALSE<-NULL
CONS_C1_df_dup_SEP_2020_match_not_miss3$edad_ini_cons<-quantiles(CONS_C1_df_dup_SEP_2020_match_not_miss3$edad_ini_cons,20)
CONS_C1_df_dup_SEP_2020_match_not_miss3$edad_al_ing<-quantiles(CONS_C1_df_dup_SEP_2020_match_not_miss3$edad_al_ing,20)
CONS_C1_df_dup_SEP_2020_match_not_miss3$fech_ing_num<-quantiles(CONS_C1_df_dup_SEP_2020_match_not_miss3$fech_ing_num,20)
match.on.sel2<-names(CONS_C1_df_dup_SEP_2020_match_not_miss3)[-c(1,2,5)]
#"edad_ini_cons","edad_al_ing","fech_ing_num")
CONS_SEP_match = data.table::data.table(CONS_C1_df_dup_SEP_2020_match_not_miss2[order(CONS_C1_df_dup_SEP_2020_match_not_miss2$tipo_de_plan_res, decreasing = TRUE), ])
CONS_SEP_match_dum = data.table::data.table(CONS_C1_df_dup_SEP_2020_match_not_miss3 %>% dplyr::arrange(factor(row, levels = CONS_SEP_match$row)))Match
The matched variables were defined for the treatments at baseline (n=84,773).
library(designmatch)
#fine = list(covs = fine_covs)
#solver = list(name = name, t_max = t_max, approximate = 1, round_cplex = 0, trace_cplex = 0).
#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:
#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:
# 1. Gurobi installation
#For an exact solution, we strongly recommend running designmatch either with CPLEX or Gurobi. Between these two solvers, the R interface of Gurobi is considerably easier to install. Here we provide general instructions for manually installing Gurobi and its R interface in Mac and Windows machines.
#1. Create a free academic license
# Follow the instructions in: http://www.gurobi.com/documentation/7.0/quickstart_windows/creating_a_new_academic_li.html
#2. Install the software
# 2.1. In http://www.gurobi.com/index, go to Downloads > Gurobi Software
# 2.2. Choose your operating system and press download
#
#3. Retrieve and set up your Gurobi license
# 2.1. Follow the instructions in: http://www.gurobi.com/documentation/7.0/quickstart_windows/retrieving_and_setting_up_.html
# 2.2. Then follow the instructions in: http://www.gurobi.com/documentation/7.0/quickstart_windows/retrieving_a_free_academic.html
#
#4. Test your license
# Follow the instructions in: http://www.gurobi.com/documentation/7.0/quickstart_windows/testing_your_license.html
#
#5. Install the R interface of Gurobi
# Follow the instructions in: http://www.gurobi.com/documentation/7.0/quickstart_windows/r_installing_the_r_package.html
# * In Windows, in R run the command install.packages("PATH\\gurobi_7.X-Y.zip", repos=NULL) where path leads to the file gurobi_7.X-Y.zip (for example PATH=C:\\gurobi702\\win64\\R; note that the path may be different in your computer), and "7.X-Y" refers to the version you are installing.
# * In MAC, in R run the command install.packages('PATH/gurobi_7.X-Y.tgz', repos=NULL) where path leads to the file gurobi_7.X-Y.tgz (for example PATH=/Library/gurobi702/mac64/R; note that the path may be different in your computer), and "7.X-Y" refers to the version you are installing.
#
#6. Test the installation
# Load the library and run the examples therein
# * A possible error that you may get is the following: "Error: package ‘slam’ required by ‘gurobi’ could not be found". If that case, install.packages('slam') and try again.
# You should be all set!
CONS_SEP_match$tipo_de_plan_res<-ifelse(CONS_SEP_match$tipo_de_plan_res=="1",1,0)
#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:
#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:#:#:#:#:#:#:#:#:#:#:#:#:#:#:##:
require(slam)
# Solver options
#default solver is glpk with approximate = 1
#For an exact solution, we strongly recommend using cplex or gurobi as they are much faster than the other solvers, but they do require a license (free for academics, but not for people outside universities)
t_max = 60*6
solver = "gurobi" #cplex, glpk, gurobi and symphony
solver = list(name = solver,
t_max = t_max, #t_max is a scalar with the maximum time limit for finding the matches.within this time limit, a partial, suboptimal solution is given
approximate = 1,#. If approximate = 1 (the default), an approximate solution is found via a relaxation of the original integer program
round_cplex = 0,
trace = 1#turns the optimizer output on
)
#Indicador de tratamiento
t_ind= ifelse(CONS_SEP_match$tipo_de_plan_res=="1",1,0)
#table(is.na(CONS_SEP_match$tipo_de_plan_res))
# Moment balance: constrain differences in means to be at most 0.1 standard deviations apart
#:#:#:#:#:#:#:#:#:#:#:#:#:
#######mom_covs is a matrix where each column is a covariate whose mean is to be balanced
#######mom_tols is a vector of tolerances for the maximum difference in means for the covariates in mom_covs
#######mom_targets is a vector of target moments (e.g., means) of a distribution to be approximated by matched sampling. is optional, but if #######mom_covs is specified then mom_tols needs to be specified too
#######The lengths of mom_tols and mom_target have to be equal to the number of columns of mom_covs
mom_covs = cbind(CONS_SEP_match$edad_al_ing,
CONS_SEP_match$fech_ing_num,
CONS_SEP_match$edad_ini_cons)
mom_tols = absstddif(mom_covs, t_ind, .0999)# original, 0.05, ahora probaré con 0.7
mom = list(covs = mom_covs, tols = mom_tols, targets = NULL)
# Mean balance
covs = cbind(CONS_SEP_match$edad_al_ing,
CONS_SEP_match$fech_ing_num,
CONS_SEP_match$edad_ini_cons)
meantab(covs, t_ind)## Mis Min Max Mean T Mean C Std Dif P-val
## [1,] 0 14.88 88.84 35.99 35.99 0 1
## [2,] 0 13621.00 18199.00 16445.33 16445.33 0 1
## [3,] 0 5.00 74.00 16.51 16.51 0 1# Fine balance
#is a matrix where each column is a nominal covariate for fine balance
fine_covs = cbind(CONS_SEP_match$origen_ingreso_mod,
CONS_SEP_match$dg_cie_10_rec,
CONS_SEP_match$sexo_2,
CONS_SEP_match$sus_ini_mod_mvv,
CONS_SEP_match$tipo_centro_pub, #cuidado
CONS_SEP_match$estado_conyugal_2,
CONS_SEP_match$escolaridad_rec,
CONS_SEP_match$freq_cons_sus_prin,
CONS_SEP_match$nombre_region,
CONS_SEP_match$condicion_ocupacional_corr,
#d_match_no_duplicates$evaluacindelprocesoteraputico,
CONS_SEP_match$dg_trs_cons_sus_or
)
fine = list(covs = fine_covs)
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
#MATCH
start.time <- Sys.time()
set.seed(2125)
out = cardmatch(t_ind, #ES NECESARIO QUE LOS TRATAMIENTOS ESTEN ORDENADOS Y LOS OTROS VECTORES TAMBIËN
mom = mom,# ya los definí list(covs = mom_covs, tols = mom_tols, targets = mom_targets),
fine = fine,
solver = solver)## Building the matching problem...
## Gurobi optimizer is open...
## Finding the optimal matches...
## Gurobi Optimizer version 9.1.0 build v9.1.0rc0 (win64)
## Thread count: 6 physical cores, 12 logical processors, using up to 12 threads
## Optimize a model with 60 rows, 84773 columns and 1441141 nonzeros
## Model fingerprint: 0xcd0b3adc
## Variable types: 0 continuous, 84773 integer (84773 binary)
## Coefficient statistics:
## Matrix range [1e+00, 2e+04]
## Objective range [1e+00, 1e+00]
## Bounds range [0e+00, 0e+00]
## RHS range [0e+00, 0e+00]
## Found heuristic solution: objective -0.0000000
## Presolve time: 1.93s
## Presolved: 60 rows, 84773 columns, 1440932 nonzeros
## Variable types: 0 continuous, 84773 integer (84773 binary)
##
## Root relaxation: objective 1.145262e+04, 342 iterations, 0.64 seconds
##
## Nodes | Current Node | Objective Bounds | Work
## Expl Unexpl | Obj Depth IntInf | Incumbent BestBd Gap | It/Node Time
##
## 0 0 11452.6186 0 31 -0.00000 11452.6186 - - 2s
## H 0 0 11452.000000 11452.6186 0.01% - 2s
## 0 0 11452.6186 0 31 11452.0000 11452.6186 0.01% - 2s
##
## Explored 1 nodes (342 simplex iterations) in 2.97 seconds
## Thread count was 12 (of 12 available processors)
##
## Solution count 2: 11452 -0
##
## Optimal solution found (tolerance 1.00e-04)
## Best objective 1.145200000000e+04, best bound 1.145200000000e+04, gap 0.0000%
## Optimal matches foundend.time <- Sys.time()
time.taken <- end.time - start.time
# Fine balance (note here we are getting an approximate solution)
#for (i in 1:ncol(fine_covs)) {
# print(finetab(fine_covs[, i], t_id_1, c_id_1))
#}
# Indices of the treated units and matched controls
t_id_1 = out$t_id
c_id_1 = out$c_id
group = out$group_id
ids_matched<-cbind.data.frame(t_id_1, c_id_1,group)
paste0("No. of treatments: ",table(table(t_id_1)) %>% formatC(big.mark = ","),"; No. of controls: ",table(table(c_id_1))%>% formatC(big.mark = ","))## [1] "No. of treatments: 11,452; No. of controls: 11,452"# Fine balance (note here we are getting an approximate solution)
finetab_match1<-data.frame()
for (i in 1:ncol(fine_covs)) {
#finetab_match1<- rbind.data.frame(
finetab(fine_covs[, i], t_id_1, c_id_1)
}
d_match = CONS_SEP_match[c(t_id_1, c_id_1), ]
paste0("Number of duplicated rows: ",d_match %>% dplyr::group_by(row) %>% dplyr::mutate(n_row=n()) %>% dplyr::ungroup() %>% dplyr::filter(n_row>1) %>% nrow())## [1] "Number of duplicated rows: 0"#cuidado, el anterior me encontró más del mismo control para un tratado
#por eso ocuparé el de más abajo
d_match_no_duplicates = CONS_SEP_match[which(CONS_SEP_match$row %in% c(t_id_1, c_id_1)), ]Explore Results of the Matching
Age at Admission
Figure 9. Empirical Cumulative Distribution Functions on the Matched Sample
Age of Onset of Drug Use
Figure 9. Empirical Cumulative Distribution Functions on the Matched Sample
Date of Admission
Figure 9. Empirical Cumulative Distribution Functions on the Matched Sample
Love plot
Figure 10. Love plot of the Matched Sample in Covariates v/s Unmatched Sample
Balance
| Variables | Nature of Variables | SMDs | Threshold | Variance Ratios | Threshold | KS | SMDs | Threshold | Variance Ratios | Threshold | KS |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Public Center | Binary | -1.18 | Not Balanced, >0.1 | 0.51 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Occ.Status-Employed | Binary | -0.95 | Not Balanced, >0.1 | 0.41 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Freq Drug Cons-Daily | Binary | 0.72 | Not Balanced, >0.1 | 0.33 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Occ.Status- Unemployed | Binary | 0.62 | Not Balanced, >0.1 | 0.30 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Drug Dependence | Binary | 0.59 | Not Balanced, >0.1 | 0.22 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Freq Drug Cons-2-3d/wk | Binary | -0.52 | Not Balanced, >0.1 | 0.21 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Motive Admission-Assisted Referral | Binary | 0.48 | Not Balanced, >0.1 | 0.17 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Occ.Status- No activity | Binary | 0.38 | Not Balanced, >0.1 | 0.11 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Starting Substance-Alcohol | Binary | -0.35 | Not Balanced, >0.1 | 0.17 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| >1 treatment | Binary | 0.33 | Not Balanced, >0.1 | 0.14 | 0.22 | Not Balanced, >0.1 | 0.10 | ||||
| ICD-10-Wo/Psych Comorbidity | Binary | -0.32 | Not Balanced, >0.1 | 0.15 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Treatments (#) | Contin. | 0.31 | Not Balanced, >0.1 | 1.91 | Balanced, <2 | 0.14 | 0.20 | Not Balanced, >0.1 | 1.42 | Balanced, <2 | 0.10 |
| Marital Status-Married/Shared liv. arr. | Binary | -0.30 | Not Balanced, >0.1 | 0.13 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Date of Admission | Contin. | -0.29 | Not Balanced, >0.1 | 1.00 | Balanced, <2 | 0.14 | -0.10 | Balanced, <0.1 | 0.93 | Balanced, <2 | 0.06 |
| Marital Status-Single | Binary | 0.29 | Not Balanced, >0.1 | 0.14 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Motive Admission-Spontaneous | Binary | -0.27 | Not Balanced, >0.1 | 0.13 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Freq Drug Cons-1d/wk or more | Binary | -0.25 | Not Balanced, >0.1 | 0.05 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| ICD-10-W/Psych Comorbidity | Binary | 0.23 | Not Balanced, >0.1 | 0.11 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Starting Substance-Marijuana | Binary | 0.23 | Not Balanced, >0.1 | 0.10 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Region-Arica(15) | Binary | 0.21 | Not Balanced, >0.1 | 0.04 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Starting Substance-Cocaine paste | Binary | 0.20 | Not Balanced, >0.1 | 0.07 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Age at Admission | Contin. | -0.19 | Not Balanced, >0.1 | 0.84 | Balanced, <2 | 0.07 | 0.06 | Balanced, <0.1 | 0.99 | Balanced, <2 | 0.04 |
| Freq Drug Cons-Less 1d/wk | Binary | -0.19 | Not Balanced, >0.1 | 0.03 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Region-Tarapacá(01) | Binary | 0.16 | Not Balanced, >0.1 | 0.03 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Sex-Women | Binary | 0.15 | Not Balanced, >0.1 | 0.07 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Occ.Status- Not seeking work | Binary | 0.15 | Not Balanced, >0.1 | 0.02 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Motive Admission-Justice Sector | Binary | -0.13 | Not Balanced, >0.1 | 0.04 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Educational Attainment-PS or less | Binary | 0.12 | Not Balanced, >0.1 | 0.06 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Region-Araucanía(09) | Binary | -0.12 | Not Balanced, >0.1 | 0.02 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Region-Magallanes(12) | Binary | -0.12 | Not Balanced, >0.1 | 0.01 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Freq Drug Cons-4-6d/wk | Binary | -0.11 | Not Balanced, >0.1 | 0.04 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Region-Antofagasta(02) | Binary | 0.11 | Not Balanced, >0.1 | 0.02 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Region-Coquimbo(04) | Binary | -0.10 | Not Balanced, >0.1 | 0.02 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Region-Aysén(11) | Binary | -0.09 | Balanced, <0.1 | 0.01 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Region-Ñuble(16) | Binary | -0.09 | Balanced, <0.1 | 0.01 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Age of Onset of Drug Use | Contin. | -0.09 | Balanced, <0.1 | 0.91 | Balanced, <2 | 0.07 | 0.00 | Balanced, <0.1 | 1.02 | Balanced, <2 | 0.01 |
| ICD-10-Dg. Unknown/under study | Binary | 0.08 | Balanced, <0.1 | 0.03 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Freq Drug Cons-Did not use | Binary | -0.08 | Balanced, <0.1 | 0.01 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Educational Attainment-HS or less | Binary | -0.07 | Balanced, <0.1 | 0.03 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Educational Attainment-More than HS | Binary | -0.06 | Balanced, <0.1 | 0.02 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Region- Biobío(08) | Binary | -0.06 | Balanced, <0.1 | 0.02 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Region-Valparaíso(05) | Binary | 0.06 | Balanced, <0.1 | 0.02 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Region-Los Lagos(10) | Binary | -0.04 | Balanced, <0.1 | 0.01 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Occ.Status-Inactive | Binary | -0.04 | Balanced, <0.1 | 0.01 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Motive Admission-Other | Binary | 0.03 | Balanced, <0.1 | 0.01 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Region-Atacama(03) | Binary | -0.03 | Balanced, <0.1 | 0.01 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Region-Maule(07) | Binary | -0.03 | Balanced, <0.1 | 0.01 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Motive Admission-Health Sector | Binary | -0.02 | Balanced, <0.1 | 0.01 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Marital Status-Widower | Binary | -0.02 | Balanced, <0.1 | 0.00 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Region-O’Higgins(06) | Binary | -0.02 | Balanced, <0.1 | 0.01 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Occ.Status-Looking 1st job | Binary | -0.02 | Balanced, <0.1 | 0.00 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Starting Substance-Other | Binary | 0.01 | Balanced, <0.1 | 0.00 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Marital Status-Separated/Divorced | Binary | -0.01 | Balanced, <0.1 | 0.00 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Region-Los Ríos(14) | Binary | -0.01 | Balanced, <0.1 | 0.00 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Region-Metropolitana(13) | Binary | -0.01 | Balanced, <0.1 | 0.01 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Starting Substance-Cocaine hydrochloride | Binary | 0.00 | Balanced, <0.1 | 0.00 | 0.00 | Balanced, <0.1 | 0.00 | ||||
| Note. Unadjusted (n=84,773) ; Adjusted (n=22,904) ; Total pairs: 11,452 |
Figure 13. Love plot of the Matched Sample in Covariates v/s Unmatched Sample
We allowed to tolerate fech_ing_num (SMD=0.11), because the date of admission not necessarily had to be strictly balanced, assuming that not every user had to be admitted to treatment in exact dates.
Survival Setting
Bivariate
irrs<-function(x, y="event", z="person_days",db){
#x= variable que agrupa
#y= evento explicado
#z= person days
#db= base de datos
fmla <- as.formula(paste0(y,"~",x))
fmla2 <- as.formula(paste0(z,"~",x))
assign(paste0("irr_",y,"_por_",x),
rateratio.test::rateratio.test(
x=as.numeric(xtabs(fmla, data=get(db)))[c(2,1)],
n=as.numeric(xtabs(fmla, data=get(db)))[c(2,1)]
)
)
return(
rateratio.test::rateratio.test(
x=as.numeric(xtabs(fmla, data=get(db)))[c(2,1)],
n=as.numeric(xtabs(fmla2, data=get(db)))[c(2,1)]
)
)
}
#CONS_C1_df_dup_SEP_2020%>%
# dplyr::filter(hash_key %in% unlist(unique(d_match$hash_key))) %>%
# janitor::tabyl(condicion_ocupacional_corr)
#
#d_match_surv %>% janitor::tabyl(duplicates_filtered,event)
#
CONS_C1_df_dup_SEP_2020_irrs_health<-
d_match %>%
dplyr::left_join(CONS_C1_df_dup_SEP_2020[c("row","dias_treat_imp_sin_na", "event", "person_days", "person_years","diff_bet_treat","motivodeegreso_mod_imp")],by="row") %>%
dplyr::left_join(ids_matched, by=c("row"="t_id_1")) %>%
dplyr::mutate(group_match=ifelse(!is.na(group),group,NA)) %>%
dplyr::select(-c_id_1,-group) %>%
dplyr::left_join(ids_matched, by=c("row"="c_id_1")) %>%
dplyr::mutate(group_match=ifelse(is.na(group_match),group,group_match)) %>%
#dplyr::filter(!is.na(group_match))
dplyr::select(-t_id_1,-group) %>%
dplyr::filter(dup==1) %>% #nrow() 85,048, QUEDARME SÓLO CON LOS CASOS QUE SON IS.NA
#dplyr::mutate(event=factor(event,labels=c("W/o Readmissions","W/Readmissions"))) %>%
#%>% janitor::tabyl(event)
dplyr::mutate(res_drop_out=dplyr::case_when(
tipo_de_plan_res==1 & abandono_temprano_rec==TRUE ~1,
TRUE~0)) %>%
dplyr::mutate(min_ach=dplyr::case_when(
evaluacindelprocesoteraputico=="3-Minimum Achievement" ~1,
TRUE~0)) %>%
dplyr::mutate(res_drop_out=factor(res_drop_out)) %>%
dplyr::mutate(min_ach=factor(min_ach)) %>%
dplyr::mutate(status_censorship=dplyr::case_when(
motivodeegreso_mod_imp=="Ongoing treatmentt" ~1,
TRUE~0))
# CONS_C1_df_dup_SEP_2020_irrs_health%>% janitor::tabyl(cnt_diagnostico_trs_fisico_irr)
#label(CONS_C1_df_dup_SEP_2020_prev4_explore$dg_fis_anemia) <- "Physical Dg. Anemia"
# cnt_mod_cie_10_or cnt_otros_probl_at_sm_or
#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_#_
irrs_early_drop<-irrs(x="abandono_temprano_rec" ,db="CONS_C1_df_dup_SEP_2020_irrs_health")
irrs_res_plan<-irrs(x="tipo_de_plan_res" ,db="CONS_C1_df_dup_SEP_2020_irrs_health")
irrs_res_early<-irrs(x="res_drop_out" ,db="CONS_C1_df_dup_SEP_2020_irrs_health")
irrs_min_ach<-irrs(x="min_ach" ,db="CONS_C1_df_dup_SEP_2020_irrs_health")The incidence rate of readmission was 1.6 (95% IC 1.51-1.69) in users that had at least an early dropout, compared with users that did not have a physical condition at baseline (p = 0.000).
Figure 12. Cum. Hazards to Experience Readmission to SUD Treatment, by Ealy Dropout of Treatment at Baseline
The incidence rate of readmission was 1.22 (95% IC 1.17-1.28) in users that had a residential plan, compared with users that had an ambulatory plan at baseline (p = 0.000).
Figure 13. Cum. Hazards to Experience Readmission to SUD Treatment, by Type of Plan at Baseline
The incidence rate of readmission was 1.64 (95% IC 1.53-1.76) in users that had a residential plan and an early dropout, compared with the rest of users at baseline (p = 0.000).
Figure 14. Cum. Hazards to Experience Readmission to SUD Treatment, whether it was a person in a Residential Treatment with an Early Dropout
The incidence rate of readmission was 1.39 (95% IC 1.33-1.46) in users that had a minimum achievement of the therapeutic goals, compared with the rest of users at baseline (p = 0.000).
Figure 15. Cum. Hazards to Experience Readmission to SUD Treatment, whether it was a person had a Minimum Achievement in Therapeutic Goals
m1 <- coxph(Surv(diff_bet_treat,event) ~ tipo_de_plan_res + strata(group_match), data = CONS_C1_df_dup_SEP_2020_irrs_health)
summary(m1)## Call:
## coxph(formula = Surv(diff_bet_treat, event) ~ tipo_de_plan_res +
## strata(group_match), data = CONS_C1_df_dup_SEP_2020_irrs_health)
##
## n= 3198, number of events= 3198
## (24349 observations deleted due to missingness)
##
## coef exp(coef) se(coef) z Pr(>|z|)
## tipo_de_plan_res 0.7695 2.1586 0.3171 2.426 0.0153 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## exp(coef) exp(-coef) lower .95 upper .95
## tipo_de_plan_res 2.159 0.4633 1.159 4.019
##
## Concordance= 0.574 (se = 0.05 )
## Likelihood ratio test= 6.19 on 1 df, p=0.01
## Wald test = 5.89 on 1 df, p=0.02
## Score (logrank) test = 6.14 on 1 df, p=0.01cox.zph(m1)#Possibly, a log-normal or log-logistic AFT model would fit better than Cox.## chisq df p
## tipo_de_plan_res 3.62 1 0.057
## GLOBAL 3.62 1 0.057#CONS_C1_df_dup_SEP_2020$condicion_ocupacional_corr CONS_C1_df_dup_SEP_2020$cnt_diagnostico_trs_fisico CONS_C1_df_dup_SEP_2020$tenencia_de_la_vivienda_mod
##COx Diagnostics
#ggcoxzph(cox.zph(m1))
#ggcoxdiagnostics(m1, type = "dfbeta",
# linear.predictions = FALSE, ggtheme = theme_bw())
#ggcoxdiagnostics(m1, type = "deviance",
# linear.predictions = FALSE, ggtheme = theme_bw())
#It’s also possible to check outliers by visualizing the deviance residuals. The deviance residual is a normalized transform of the martingale residual. These residuals should be roughtly symmetrically distributed about zero with a standard deviation of 1.
#Positive values correspond to individuals that “died too soon” compared to expected survival times.
#Negative values correspond to individual that “lived too long”.
#Very large or small values are outliers, which are poorly predicted by the model.There was evidence of proportional hazards. Users in residential treatments experience 116% within the study period than users in outpatient treatments (95% CI: 16% - 302%; p=0.0153).
Multivariate
| 0 | 1 | p.overall | |
|---|---|---|---|
| N=19858 | N=17899 | ||
| Motive of Admission to Treatment (First Entry): | <0.001 | ||
| Spontaneous | 7972 (40.1%) | 6656 (37.2%) | |
| Assisted Referral | 3434 (17.3%) | 3533 (19.7%) | |
| Other | 1128 (5.68%) | 1111 (6.21%) | |
| Justice Sector | 1405 (7.08%) | 1198 (6.69%) | |
| Health Sector | 5919 (29.8%) | 5401 (30.2%) | |
| Psychiatric Comorbidity: | 0.094 | ||
| Without psychiatric comorbidity | 5501 (27.7%) | 4795 (26.8%) | |
| Diagnosis unknown (under study) | 4111 (20.7%) | 3815 (21.3%) | |
| With psychiatric comorbidity | 10246 (51.6%) | 9289 (51.9%) | |
| Sexo Usuario/Sex of User: | 0.009 | ||
| Men | 13262 (66.8%) | 12179 (68.0%) | |
| Women | 6596 (33.2%) | 5720 (32.0%) | |
| Age at Admission to Treatment | 32.5 [26.7;40.4] | 32.9 [26.8;40.8] | 0.045 |
| Treatment Length (>90): | <0.001 | ||
| FALSE | 16292 (82.0%) | 14346 (80.1%) | |
| TRUE | 3566 (18.0%) | 3545 (19.8%) | |
| ‘Missing’ | 0 (0.00%) | 8 (0.04%) | |
| Treatments by User (#): | 0.003 | ||
| 1 | 10354 (52.1%) | 9157 (51.2%) | |
| 2 | 5348 (26.9%) | 4779 (26.7%) | |
| 3 | 2459 (12.4%) | 2281 (12.7%) | |
| 4 | 1054 (5.31%) | 986 (5.51%) | |
| 5 | 385 (1.94%) | 420 (2.35%) | |
| 6 | 189 (0.95%) | 177 (0.99%) | |
| 7 | 50 (0.25%) | 63 (0.35%) | |
| 8 | 19 (0.10%) | 36 (0.20%) | |
| More than one treatment: | 0.058 | ||
| 0 | 10354 (52.1%) | 9157 (51.2%) | |
| 1 | 9504 (47.9%) | 8742 (48.8%) | |
| Starting Substance: | 0.001 | ||
| Alcohol | 8227 (41.4%) | 7048 (39.4%) | |
| Cocaine hydrochloride | 849 (4.28%) | 744 (4.16%) | |
| Cocaine paste | 3640 (18.3%) | 3464 (19.4%) | |
| Marijuana | 6686 (33.7%) | 6215 (34.7%) | |
| Other | 456 (2.30%) | 428 (2.39%) | |
| Marital Status: | <0.001 | ||
| Married/Shared living arrangements | 5007 (25.2%) | 4202 (23.5%) | |
| Separated/Divorced | 2179 (11.0%) | 1879 (10.5%) | |
| Single | 12460 (62.7%) | 11648 (65.1%) | |
| Widower | 212 (1.07%) | 170 (0.95%) | |
| Educational Attainment: | 0.034 | ||
| 3-Completed primary school or less | 6205 (31.2%) | 5798 (32.4%) | |
| 2-Completed high school or less | 10202 (51.4%) | 9110 (50.9%) | |
| 1-More than high school | 3451 (17.4%) | 2991 (16.7%) | |
| Frequency of use of primary drug: | <0.001 | ||
| 1 day a week or more | 670 (3.37%) | 381 (2.13%) | |
| 2 to 3 days a week | 2882 (14.5%) | 1912 (10.7%) | |
| 4 to 6 days a week | 2899 (14.6%) | 2436 (13.6%) | |
| Daily | 12612 (63.5%) | 12866 (71.9%) | |
| Did not use | 364 (1.83%) | 119 (0.66%) | |
| Less than 1 day a week | 431 (2.17%) | 185 (1.03%) | |
| Public Center: | <0.001 | ||
| FALSE | 11591 (58.4%) | 12884 (72.0%) | |
| TRUE | 8267 (41.6%) | 5015 (28.0%) | |
| Evaluation of the Therapeutic Process: | <0.001 | ||
| 1-High Achievement | 3100 (15.6%) | 4092 (22.9%) | |
| 2-Medium Achievement | 5779 (29.1%) | 5894 (32.9%) | |
| 3-Minimum Achievement | 9863 (49.7%) | 7243 (40.5%) | |
| ‘Missing’ | 1116 (5.62%) | 670 (3.74%) | |
| Drug Dependence: | <0.001 | ||
| FALSE | 2351 (11.8%) | 1529 (8.54%) | |
| TRUE | 17507 (88.2%) | 16370 (91.5%) | |
| Age of Onset of Drug Use | 15.0 [14.0;17.0] | 15.0 [13.0;17.0] | 0.001 |
| Occupational Status: | <0.001 | ||
| Employed | 4396 (22.1%) | 2478 (13.8%) | |
| Inactive | 2227 (11.2%) | 1860 (10.4%) | |
| Looking for a job for the first time | 37 (0.19%) | 29 (0.16%) | |
| No activity | 2007 (10.1%) | 2295 (12.8%) | |
| Not seeking for work | 427 (2.15%) | 477 (2.66%) | |
| Unemployed | 10764 (54.2%) | 10760 (60.1%) | |
| Days of Treatment (missing dates of discharge were replaced with difference from 2019-11-13) | 155 [85.0;283] | 153 [68.0;278] | <0.001 |
| Users with Posterior Treatments (1=Readmission): | 0.058 | ||
| 0 | 10354 (52.1%) | 9157 (51.2%) | |
| 1 | 9504 (47.9%) | 8742 (48.8%) | |
| User’s Days available in the system for the study | 410 [147;1184] | 396 [153;1113] | 0.008 |
| User’s Years available in the system for the study | 1.12 [0.40;3.24] | 1.08 [0.42;3.05] | 0.008 |
| Days of difference between the Next Treatment | 377 [145;855] | 287 [81.0;762] | <0.001 |
| Cause of Discharge: | . | ||
| Late Drop-out | 7174 (36.1%) | 3644 (20.4%) | |
| Early Drop-out | 3566 (18.0%) | 3545 (19.8%) | |
| Administrative discharge | 1800 (9.06%) | 2248 (12.6%) | |
| Therapeutic discharge | 3645 (18.4%) | 5293 (29.6%) | |
| Referral to another treatment | 2557 (12.9%) | 2497 (14.0%) | |
| Ongoing treatment | 1116 (5.62%) | 664 (3.71%) | |
| ‘Missing’ | 0 (0.00%) | 8 (0.04%) | |
| Early Drop-out & Residential Plan: | 0.000 | ||
| 0 | 19858 (100%) | 14354 (80.2%) | |
| 1 | 0 (0.00%) | 3545 (19.8%) | |
| Minimum achievement of therapeutic goals: | <0.001 | ||
| 0 | 9995 (50.3%) | 10656 (59.5%) | |
| 1 | 9863 (49.7%) | 7243 (40.5%) | |
| Note. Variables of C1 dataset had to be standardized before comparison; | |||
| Continuous variables are presented as Medians and Percentiles 25 and 75 were shown; | |||
| Categorical variables are presented as number (%) |
After matching, we selected 37,757 treatments (users=22,904).
#NOT DUPLICATES
#d_match_surv %>%
# dplyr::group_by(hash_key) %>%
# dplyr::mutate(dis_hash=n_distinct(n_hash)) %>%
# dplyr::ungroup() %>%
# dplyr::filter(dis_hash>1)
set.seed(2125)
random__users <-
d_match_surv %>%
dplyr::group_by(n_hash) %>%
summarise() %>%
sample_n(1000)
d_match_surv_sub_sample<-
d_match_surv %>%
dplyr::filter(n_hash %in% unlist(random__users))
library("frailtySurv")
memory.limit(size = 20000)## [1] 20000#frailty_1<-
#fitfrail(Surv(dias_treat_imp_sin_na,event)~ tipo_de_plan_res+ cluster(hash_key),d_match_surv,frailty="gamma")
m3 <- coxph(Surv(dias_treat_imp_sin_na,event) ~ tipo_de_plan_res + frailty(hash_key,
distribution = "gaussian", sparse = FALSE, method = "reml"), data = d_match_surv_sub_sample)
summary(m3)## Call:
## coxph(formula = Surv(dias_treat_imp_sin_na, event) ~ tipo_de_plan_res +
## frailty(hash_key, distribution = "gaussian", sparse = FALSE,
## method = "reml"), data = d_match_surv_sub_sample)
##
## n= 1635, number of events= 800
##
## coef se(coef) se2 Chisq DF p
## tipo_de_plan_res1 0.1803 0.1013 0.08734 3.17 1.0 7.5e-02
## frailty(hash_key, distrib 957.93 401.1 1.7e-47
##
## exp(coef) exp(-coef) lower .95 upper .95
## tipo_de_plan_res1 1.1975 0.83504 0.98197 1.4604
## gauss:007ea2d946076132c4f 0.9075 1.10198 0.07105 11.5902
## gauss:008352994b73e152bdd 0.2812 3.55660 0.04752 1.6635
## gauss:00f06c2d87e3c936f73 0.4276 2.33883 0.06000 3.0468
## gauss:00f8499f122c17912ff 0.4993 2.00292 0.06421 3.8818
## gauss:010da44a55a56eecf8a 0.8362 1.19587 0.07162 9.7627
## gauss:014d061e60dac6baf04 0.7943 1.25904 0.07165 8.8041
## gauss:01dfd36220d380671d3 2.4353 0.41063 1.00857 5.8802
## gauss:01f7161f62a5ad1eb7d 0.8222 1.21620 0.07166 9.4346
## gauss:0201ccf5b7cda901d44 0.9165 1.09110 0.26804 3.1338
## gauss:02191e68784f4d1cc0c 0.6774 1.47629 0.07041 6.5168
## gauss:023f16b01f6e9bab198 0.9651 1.03620 0.07013 13.2801
## gauss:027d99e4a5a34f25951 0.7138 1.40095 0.07101 7.1749
## gauss:02a37b1c8cd08e1a244 0.9400 1.06387 0.07058 12.5184
## gauss:02d83baec85facae983 0.9604 1.04124 0.27976 3.2970
## gauss:02da02466c5169a3cf2 0.3281 3.04824 0.05224 2.0603
## gauss:02ddafac9dddfd88a3b 0.9400 1.06387 0.07058 12.5184
## gauss:02f5c347f5bf3fdd109 0.4586 2.18055 0.06196 3.3944
## gauss:0315566c7445683dc9e 5.9146 0.16907 1.73123 20.2066
## gauss:0331102e812b1d4fd83 3.1470 0.31776 0.76092 13.0153
## gauss:036293bded44907bdaf 28.9340 0.03456 8.66416 96.6252
## gauss:03b2eef4613e77fc2b2 0.9822 1.01808 0.06978 13.8257
## gauss:03bd638c4f0ea14cef8 4.5731 0.21867 1.02050 20.4934
## gauss:048a05a72669d838dca 0.9569 1.04507 0.07029 13.0271
## gauss:04f87ddce93092e6f9f 0.4435 2.25469 0.06104 3.2225
## gauss:05218f7c7390f11e7bb 0.8745 1.14352 0.07139 10.7117
## gauss:0554ed612d508792004 3.0526 0.32759 0.96588 9.6477
## gauss:056fd61aa0e6a067cf2 0.5853 1.70839 0.06791 5.0451
## gauss:0596364f02cb2a42a5e 0.5227 1.91311 0.06536 4.1803
## gauss:059e769c77187ec7898 4.9577 0.20171 1.48277 16.5761
## gauss:05d8ddc18a5e57ff7f3 0.4811 2.07843 0.06325 3.6598
## gauss:05fd54958804a587eba 0.6425 1.55650 0.06963 5.9282
## gauss:06aa6981155cbb0588a 0.5791 1.72683 0.06769 4.9541
## gauss:06c3d03fd9c57214bf6 0.8610 1.16147 0.07150 10.3680
## gauss:06c74fa52291fbb703d 0.5005 1.99793 0.06428 3.8975
## gauss:06f982e0ed0729c108f 2.9388 0.34028 0.72006 11.9939
## gauss:0720ad02f4b4f90adf8 0.3477 2.87610 0.05393 2.2416
## gauss:07deb31e63b98514f7f 0.3030 3.30002 0.04981 1.8436
## gauss:0836ffb3d140940cf2d 0.7954 1.25731 0.07165 8.8284
## gauss:0868af2f47876079efd 0.5599 1.78597 0.20245 1.5486
## gauss:086d54c81e662702484 0.7303 1.36927 0.07122 7.4886
## gauss:0879c339e0a12a515c7 0.7384 1.35434 0.07131 7.6456
## gauss:08ad06a6707f3de0b95 5.0763 0.19699 1.10454 23.3297
## gauss:08c81716b74aa5a66f0 0.8046 1.24291 0.07167 9.0323
## gauss:08ee576898887f53153 0.8587 1.16455 0.07151 10.3111
## gauss:095c145feba7dd9f2be 0.9009 1.10997 0.07113 11.4115
## gauss:09abef586aac0101d55 0.9300 1.07523 0.07074 12.2281
## gauss:09fb4892c7b8f0b787c 0.7068 1.41474 0.07091 7.0455
## gauss:0a15e6490832aa35b82 0.8263 1.21024 0.07165 9.5286
## gauss:0a4ab4d1b360ba83b23 0.9431 1.06036 0.07053 12.6105
## gauss:0a99d14bd301e93fc13 0.3381 2.95755 0.10822 1.0564
## gauss:0acb98be76a7ae2e4da 0.3856 2.59319 0.05700 2.6089
## gauss:0b03ee3a1dc1fc330ef 0.9023 1.10829 0.07111 11.4485
## gauss:0b2cb4f5f4062c2699b 0.9569 1.04507 0.07029 13.0271
## gauss:0b4ffd8c59af47af722 0.9075 1.10198 0.07105 11.5902
## gauss:0b55d6fbd1e6c6c2307 1.3748 0.72737 0.53212 3.5520
## gauss:0b62dfeddc77a30ed11 5.0143 0.19943 1.09413 22.9800
## gauss:0b83e7e42af93d6c1a3 0.3501 2.85659 0.05413 2.2638
## gauss:0ba5e9f27e9898b5035 0.6979 1.43285 0.07077 6.8823
## gauss:0bc04019cd2f7164d02 0.8581 1.16540 0.07152 10.2955
## gauss:0c59cd333790128b502 0.3807 2.62697 0.05662 2.5594
## gauss:0cb473217468910f4f7 3.1866 0.31382 1.00207 10.1333
## gauss:0cf40e84f80c62a3b49 0.9131 1.09513 0.07098 11.7478
## gauss:0d20e137bcb8e4304ab 0.8877 1.12650 0.07127 11.0564
## gauss:0d83b3b76160d24470f 3.0157 0.33160 0.73503 12.3729
## gauss:0d882135aa697ccc756 0.9082 1.10110 0.31728 2.5996
## gauss:0e0c9e7cec37653d4a4 1.0331 0.96798 0.29768 3.5852
## gauss:0e91dec8dc3e152944e 0.8100 1.23459 0.07167 9.1544
## gauss:0eb0b3e8a888df4719f 11.2049 0.08925 1.91407 65.5937
## gauss:0edd6e28398398f3097 0.9875 1.01265 0.06967 13.9968
## gauss:0f1218127d537080631 3.9081 0.25588 1.58366 9.6441
## gauss:0fa2a8921e91a0d050c 0.4398 2.27371 0.16008 1.2084
## gauss:0fd14d475cac0fdc717 0.8956 1.11653 0.07119 11.2684
## gauss:10081af31756d92d0d6 0.5494 1.82022 0.06654 4.5361
## gauss:10cafbcc3d4195f8589 0.7377 1.35562 0.07130 7.6320
## gauss:10cea4f4aeafcc0caa8 0.8801 1.13629 0.07135 10.8555
## gauss:1166017c66ce634ce82 1.4361 0.69634 0.55334 3.7270
## gauss:117b7a579e44ffb5f96 4.1605 0.24036 1.49935 11.5446
## gauss:11c843021aca505c243 0.8874 1.12688 0.07127 11.0486
## gauss:11f5905553447e3f2a9 0.9191 1.08806 0.07090 11.9145
## gauss:11fa6e5dcacf4cedd2b 0.6494 1.53983 0.06980 6.0423
## gauss:12307c9754026623de4 0.4334 2.30716 0.06039 3.1110
## gauss:12b3fe47c00c74e397f 0.4938 2.02515 0.06393 3.8138
## gauss:12cacb79639f6553536 0.9512 1.05129 0.07039 12.8547
## gauss:12ed2d53fb0737a33d9 1.3009 0.76871 0.50179 3.3726
## gauss:12fdd9404bcde15b4d4 0.8209 1.21816 0.07166 9.4037
## gauss:1333df4703ecf0912ba 0.7605 1.31490 0.07150 8.0894
## gauss:13481cab691dd2f3e25 0.5527 1.80933 0.06667 4.5816
## gauss:13b7f0af65998b4c86e 0.8243 1.21319 0.07166 9.4817
## gauss:13d91c42c6c55b75931 0.6342 1.57673 0.06942 5.7947
## gauss:13effdbf0e6f9bd0787 0.7879 1.26916 0.07163 8.6666
## gauss:13f4537ea7bf1738830 0.7349 1.36076 0.07127 7.5772
## gauss:1439099edf57c0d4468 0.4571 2.18759 0.06187 3.3774
## gauss:147caccb4f8ba964066 1.8986 0.52669 0.71971 5.0087
## gauss:147e0b15b265487ccd8 1.3044 0.76661 0.44425 3.8302
## gauss:14d5828aa7f49e48d11 0.1731 5.77752 0.04417 0.6783
## gauss:162eb6d29a39a8cce3b 1.2875 0.77670 0.44001 3.7672
## gauss:1688fde0b9ecf1e5c3d 1.3062 0.76560 0.44678 3.8186
## gauss:16b925b917c522b6e06 0.4062 2.46178 0.05852 2.8194
## gauss:16cfffcd52200f1a900 0.8801 1.13629 0.07135 10.8555
## gauss:170134cf188b14f6413 0.8406 1.18968 0.07161 9.8671
## gauss:170e642f08bbf9e664e 0.7303 1.36927 0.07122 7.4886
## gauss:17429b578e18c6cdc96 2.1690 0.46104 0.70834 6.6417
## gauss:17453be723459c6d85b 1.9670 0.50838 0.51829 7.4653
## gauss:185db17f8630f961ce5 8.0849 0.12369 2.77159 23.5842
## gauss:187e5ca29667f17665c 0.4333 2.30797 0.06038 3.1093
## gauss:188a090e1443f1d1485 1.5938 0.62744 0.43392 5.8539
## gauss:19143fc503e6e180573 0.2509 3.98539 0.04415 1.4261
## gauss:198a09fc659930edb77 0.9063 1.10335 0.26509 3.0987
## gauss:198fbfc7211ab565bbb 0.4834 2.06881 0.06338 3.6866
## gauss:199873ed43595e5b1d0 0.6323 1.58156 0.06936 5.7636
## gauss:19a4afc73fd0345bcee 0.7169 1.39486 0.07105 7.2335
## gauss:19cdcec84063ed53c36 2.2220 0.45005 0.91946 5.3697
## gauss:1a030423d7d4640383d 1.7734 0.56389 0.58987 5.3316
## gauss:1a52a78ee627d9a5b73 0.5451 1.83456 0.06636 4.4777
## gauss:1ac5a611f15b0602ef3 0.9424 1.06114 0.07054 12.5901
## gauss:1b3a9140e5cced584ea 0.8012 1.24806 0.07166 8.9586
## gauss:1b47fedd6c4823ebe52 0.7035 1.42137 0.07086 6.9850
## gauss:1b7b08ce3772fc12d5b 1.3832 0.72294 0.47014 4.0698
## gauss:1b81ee24dcc5d364990 3.9806 0.25122 0.91744 17.2715
## gauss:1bb1723d4f510552bbd 0.8735 1.14485 0.07140 10.6852
## gauss:1bba3ca0d08fb0a6dfd 0.3500 2.85698 0.05411 2.2640
## gauss:1c58026bd884f8bcde9 0.9753 1.02536 0.06993 13.6015
## gauss:1c78a51c8c50f85a097 0.5296 1.88836 0.06568 4.2700
## gauss:1c9b69eefe0c6d6f178 0.2812 3.55660 0.04752 1.6635
## gauss:1cbf28e502d24c384ea 0.5302 1.88617 0.06570 4.2781
## gauss:1d67ed962fd8cef8020 0.2099 4.76325 0.03941 1.1184
## gauss:1d695819cbd811487e9 0.9179 1.08950 0.07091 11.8802
## gauss:1d799e424aaf041c7da 0.6833 1.46357 0.07052 6.6202
## gauss:1db1bad18a676ab96fb 0.9252 1.08081 0.07081 12.0899
## gauss:1dd0d0114c583a72c49 1.7519 0.57082 0.46954 6.5362
## gauss:1e08f8e5bd2c5fd611b 0.7577 1.31985 0.07148 8.0310
## gauss:1e73b34cd39a00fee11 0.9487 1.05409 0.07043 12.7783
## gauss:1ec051b31ea981e621c 0.8556 1.16875 0.07153 10.2344
## gauss:1ee7e0d56ceb73752ed 0.8661 1.15454 0.07146 10.4981
## gauss:1f1ccb001aab950c0b5 1.7398 0.57477 0.46653 6.4884
## gauss:2011ecceba9aee0b3e0 0.8002 1.24973 0.07166 8.9353
## gauss:201fc23534e744aca7d 3.5975 0.27797 1.11643 11.5922
## gauss:205a5dfa7879ef8e801 0.7219 1.38528 0.07112 7.3269
## gauss:206f319817bb0bd7259 0.6023 1.66039 0.06848 5.2968
## gauss:20b6b591d8dba10db06 0.8727 1.14582 0.07141 10.6665
## gauss:20f2bd5f601f34ac2b4 12.9057 0.07749 2.08057 80.0536
## gauss:217800aa95013f56269 0.9327 1.07220 0.07070 12.3043
## gauss:2182052d5072d9a8171 0.6031 1.65802 0.06851 5.3099
## gauss:21a0968fb458f7974ab 0.5203 1.92208 0.06525 4.1485
## gauss:21e1a0cb1dd23fabdb6 1.2607 0.79320 0.35444 4.4843
## gauss:22394e09648923bc3bb 0.7626 1.31136 0.07151 8.1317
## gauss:2264767426c0edee7a8 1.6757 0.59677 0.45284 6.2006
## gauss:22a071095c7e3cbab81 0.6961 1.43655 0.07075 6.8495
## gauss:22ec4b7ee25ce54c5d0 0.9410 1.06269 0.07056 12.5491
## gauss:23938bd85a47c2e8730 1.6807 0.59500 0.56317 5.0157
## gauss:24cc31d1070e2cecc23 4.2080 0.23764 0.95776 18.4885
## gauss:24eb3c07a59960257d8 0.6857 1.45830 0.07056 6.6639
## gauss:24f9f2b028a51c0284b 0.9785 1.02197 0.06986 13.7051
## gauss:257ad96592ae888ce57 0.5296 1.88836 0.06568 4.2700
## gauss:25ba4f3808acc718618 1.4158 0.70630 0.39157 5.1194
## gauss:261ae547e1be602ac22 0.7701 1.29860 0.07156 8.2870
## gauss:265830f1b6be74caf85 0.9527 1.04963 0.07036 12.9002
## gauss:266bdef9550dc71e6ab 1.7295 0.57819 0.66188 4.5194
## gauss:26c1063710fa9817d44 8.1990 0.12197 2.29738 29.2608
## gauss:26c2097cfb34c83b089 0.9693 1.03171 0.07005 13.4116
## gauss:26ea27ea2ea6f0142d0 0.5921 1.68880 0.06814 5.1455
## gauss:2725baa8a93d2373361 0.4490 2.22719 0.06138 3.2847
## gauss:273dd1b0ba6c1331930 0.6583 1.51903 0.07000 6.1911
## gauss:2799b3eddcd029fe7cf 0.7404 1.35067 0.07133 7.6851
## gauss:27b798f545e657a561f 0.4448 2.24801 0.06112 3.2377
## gauss:27d5052ff68edb71597 0.3127 3.19791 0.05075 1.9268
## gauss:280892a7b0c725e7dfc 0.9191 1.08806 0.07090 11.9145
## gauss:282dcee8808a3ff7da7 0.7067 1.41512 0.07091 7.0426
## gauss:28c577e448d08f62b5e 0.8336 1.19965 0.07163 9.7004
## gauss:28fbdd4baa57c897c5c 0.7980 1.25309 0.34041 1.8709
## gauss:29b46a683fc05021865 0.9727 1.02804 0.06998 13.5207
## gauss:29e5e6b94ad6e5ee3c0 0.8415 1.18842 0.07160 9.8884
## gauss:29f382d0469295e2c44 0.7908 1.26456 0.07164 8.7285
## gauss:2a278e9b9af7accdcc6 0.6550 1.52674 0.06993 6.1348
## gauss:2ab1f6dd08289f7f4d7 0.9410 1.06269 0.07056 12.5491
## gauss:2ac77ced38cf976dbf9 6.1114 0.16363 2.40985 15.4986
## gauss:2adfa7e2f6d763c1c6c 0.7036 1.42132 0.07087 6.9852
## gauss:2adfc29130134c4ebe3 0.8762 1.14128 0.07138 10.7558
## gauss:2b05251ca8a43ea9bc2 0.8046 1.24291 0.07167 9.0323
## gauss:2b45294e123346196cd 1.5620 0.64021 0.42556 5.7331
## gauss:2bb4f0e4da1468c072a 0.4182 2.39107 0.05937 2.9461
## gauss:2c0cec23dab521f7ad4 0.7845 1.27469 0.07162 8.5926
## gauss:2c1e3d30b4cf0bb3aa9 0.9342 1.07039 0.07067 12.3501
## gauss:2c66c6c38e8fe228395 2.7748 0.36038 1.14318 6.7353
## gauss:2d29ed0d67f537b975a 0.9741 1.02654 0.06995 13.5658
## gauss:2d65d267eb30a41f5d0 1.4776 0.67676 0.40603 5.3774
## gauss:2d88874e2fc3699c702 0.9698 1.03112 0.07004 13.4291
## gauss:2e1c56aa33afb7ff414 0.9300 1.07523 0.07074 12.2281
## gauss:2e96ced3e0522d25139 2.5122 0.39806 0.63455 9.9457
## gauss:2eba237e68baba8a003 0.8415 1.18842 0.07160 9.8884
## gauss:2ee55d6b75d8b63e9f5 6.0520 0.16524 2.12458 17.2393
## gauss:2f8b191cb9bbeb8db4b 0.9617 1.03988 0.07020 13.1741
## gauss:2fc83220d8f89612e57 0.9279 1.07769 0.07077 12.1667
## gauss:2fdef577ad89d929a1d 0.8877 1.12650 0.07127 11.0564
## gauss:304befe1675aa804445 0.5840 1.71242 0.06786 5.0251
## gauss:305c5a66dc4021cb80f 0.8300 1.20476 0.07164 9.6168
## gauss:308ddedf96ca58101b7 0.7626 1.31136 0.07151 8.1317
## gauss:30f0942761236252c1c 0.8524 1.17320 0.07155 10.1541
## gauss:30f85cbc46961f2cfed 0.2803 3.56769 0.04748 1.6546
## gauss:31190931bf4e2fa0024 0.9247 1.08144 0.07082 12.0745
## gauss:31d6cab05713042ca31 0.4448 2.24801 0.06112 3.2377
## gauss:326bfb165db003204f2 0.9353 1.06916 0.07065 12.3815
## gauss:32c11efca6615ff4f23 0.8806 1.13555 0.07134 10.8708
## gauss:32ee4941a9c04f937cd 0.9179 1.08950 0.07091 11.8802
## gauss:3310a1613a1336735a2 2.0248 0.49389 0.52993 7.7362
## gauss:33952a8f9e2eaf56e79 2.3994 0.41676 0.77615 7.4178
## gauss:33e30cc7be8146ab2de 0.8151 1.22690 0.07167 9.2697
## gauss:348796881c5fa72f815 0.9512 1.05129 0.07039 12.8547
## gauss:3501d2d82c634d19dce 8.9859 0.11129 1.66036 48.6319
## gauss:35091fa90083f3c0cae 0.8336 1.19965 0.07163 9.7004
## gauss:3539912198342dbbd0c 0.4745 2.10755 0.06288 3.5804
## gauss:35425286801539bfd5e 0.7584 1.31861 0.07148 8.0460
## gauss:35524193ac6af15b8b4 0.2631 3.80060 0.04573 1.5140
## gauss:35b21e088752c9c7a03 0.9746 1.02605 0.06994 13.5807
## gauss:36180ac7d3ec0bc5c65 0.6425 1.55650 0.06963 5.9282
## gauss:3620cc0d1f0d50bd83d 0.8965 1.11543 0.07118 11.2922
## gauss:36a71b0c1b3e25d88f4 0.8094 1.23556 0.07167 9.1398
## gauss:36d302e691cfd02ad0a 0.3336 2.99724 0.05267 2.1134
## gauss:3845d9ff2347fea084b 0.5853 1.70839 0.06791 5.0451
## gauss:390aa46f16e635ff3b9 0.8145 1.22772 0.07167 9.2574
## gauss:393f310d2feefdb11f3 0.7060 1.41636 0.07090 7.0305
## gauss:394eb86c6a7d9a8b474 19.1016 0.05235 2.53903 143.7052
## gauss:396f6fd713143c5b120 6.3878 0.15655 1.85571 21.9887
## gauss:399500a8a7a71e7f90b 0.9410 1.06269 0.07056 12.5491
## gauss:39aae0962b4604203bb 0.4276 2.33883 0.06000 3.0468
## gauss:39c42f817559f209c14 0.6441 1.55260 0.06967 5.9546
## gauss:39c72b24f5231a2ef73 0.5655 1.76847 0.06718 4.7595
## gauss:3a386175a587f6a502a 2.7490 0.36377 1.01954 7.4121
## gauss:3a573de0cdadf7c2500 1.7107 0.58456 0.46023 6.3586
## gauss:3a9ec880b1f91bbb559 0.9441 1.05920 0.07051 12.6412
## gauss:3ad1e5e69595b083893 0.7226 1.38380 0.07113 7.3416
## gauss:3b37813d7ca4b749f1d 0.5165 1.93628 0.06507 4.0993
## gauss:3b3c8b37d97f67398f4 0.9233 1.08308 0.07084 12.0346
## gauss:3b3e9b10dc582dfab4c 0.3350 2.98509 0.05282 2.1248
## gauss:3b68c0eb2fb68d22c1d 0.9567 1.04525 0.07029 13.0218
## gauss:3b7ecb92173cf4f8957 0.8543 1.17057 0.07154 10.2013
## gauss:3bab20e73430fc21991 0.7178 1.39311 0.07107 7.2505
## gauss:3bbfc58dfceab3459ed 2.3123 0.43247 0.59190 9.0331
## gauss:3bda80da43ea9405a48 0.8209 1.21816 0.07166 9.4037
## gauss:3bfca63955abd377f2c 8.1691 0.12241 2.28666 29.1839
## gauss:3c0b0e30c7c259848e9 3.4368 0.29097 1.07404 10.9976
## gauss:3c24b21b6709ee91ed4 0.3501 2.85659 0.05413 2.2638
## gauss:3c92fb39f0a82a1c1b3 0.8985 1.11302 0.07116 11.3444
## gauss:3cba3af00e8a74359dd 0.3985 2.50972 0.05799 2.7379
## gauss:3cf041d09d72071dc89 0.6425 1.55650 0.06963 5.9282
## gauss:3cf93cb728e47a8c07d 0.6371 1.56959 0.06949 5.8412
## gauss:3cfb68ea7a2da237dcf 0.6874 1.45482 0.07059 6.6930
## gauss:3d02129ab63b1cf492c 0.7475 1.33778 0.07140 7.8262
## gauss:3d38377330aff686fea 0.6165 1.62211 0.06892 5.5145
## gauss:3d429239a9d140dc5d7 0.7270 1.37559 0.07118 7.4243
## gauss:3dced3b8ae40fd8b08b 0.9300 1.07523 0.07074 12.2281
## gauss:3e119466525e423aa62 0.9263 1.07956 0.07079 12.1206
## gauss:3e3d3d2c51d5d6c5172 0.5788 1.72761 0.06768 4.9504
## gauss:3e9e4fedc29b9f7f85d 2.8951 0.34541 0.92191 9.0918
## gauss:3ebbbae1bf191a79b2e 0.9482 1.05465 0.07044 12.7631
## gauss:3efa15a84166016175c 4.4353 0.22546 1.34404 14.6364
## gauss:3f443c22f4172791f91 0.7141 1.40046 0.07102 7.1794
## gauss:3f4b602aaf1ffa4255a 0.9335 1.07121 0.07068 12.3293
## gauss:3f6d11489d3519d7b4f 0.9801 1.02029 0.06983 13.7570
## gauss:3fb29d101339f40ca18 0.8408 1.18934 0.07161 9.8727
## gauss:40492a3c70af46144ee 0.9451 1.05805 0.07049 12.6718
## gauss:406ebd325507a48f3bd 0.7827 1.27759 0.07162 8.5547
## gauss:4080f4ae119e74f7fa5 0.8253 1.21167 0.07165 9.5063
## gauss:408ea31ed4af25dd9f0 0.5484 1.82361 0.06649 4.5223
## gauss:40c247e0834f8cbb429 0.9676 1.03350 0.07008 13.3590
## gauss:411d5a29773286049d5 0.6514 1.53512 0.06985 6.0755
## gauss:413ef98cc27671334ae 0.7431 1.34573 0.07136 7.7384
## gauss:41413b6d6e8e5d9db8b 0.7709 1.29714 0.07156 8.3055
## gauss:416ad66bcba26a038e3 0.6874 1.45482 0.07059 6.6930
## gauss:417aa4489b9112746d1 0.6620 1.51064 0.07009 6.2524
## gauss:41d3832fc3978051c83 2.7261 0.36683 0.67749 10.9689
## gauss:41d45e51c75a7d9f780 0.8342 1.19870 0.07163 9.7158
## gauss:4244706a66016522725 0.3214 3.11165 0.05157 2.0027
## gauss:4293f59f947392fe0f4 4.7578 0.21018 1.05287 21.4995
## gauss:42cf4bc71f08f4838f4 0.7141 1.40046 0.07102 7.1794
## gauss:43401f52c54c780cc3d 0.9247 1.08144 0.07082 12.0745
## gauss:43727a597fc1b478e0e 12.6872 0.07882 4.17342 38.5688
## gauss:43d1ba9dea49ca23cb5 15.0575 0.06641 3.83582 59.1082
## gauss:441c67c5ad4471601bf 0.6531 1.53106 0.06989 6.1039
## gauss:4483d831cdbacbffeab 0.6352 1.57436 0.06944 5.8102
## gauss:44a099d4edcf891e232 0.9188 1.08834 0.07090 11.9080
## gauss:44db512e2185ef37854 0.9503 1.05235 0.07040 12.8258
## gauss:44e885dd7a01af3721d 0.5051 1.97989 0.06451 3.9545
## gauss:4567b62e549fc84dbf9 2.0694 0.48323 0.67942 6.3032
## gauss:45e33193821cae261af 0.7349 1.36076 0.07127 7.5772
## gauss:45ed975bcbdf52b3d2e 0.6986 1.43143 0.07079 6.8946
## gauss:463c106af4df632ddc6 0.6721 1.48785 0.07030 6.4255
## gauss:46f17c2b6cac24e17f2 1.8893 0.52930 0.50018 7.1364
## gauss:46f373689f3aa47d6a0 1.4731 0.67886 0.40596 5.3451
## gauss:4722cb9f140f6a14f77 0.8522 1.17340 0.07155 10.1508
## gauss:4749a598b8b185b0fc8 0.9075 1.10198 0.07105 11.5902
## gauss:475be140713fcda09ca 0.5737 1.74295 0.06749 4.8772
## gauss:475d4eb3522e8ca82e6 0.3030 3.30002 0.04981 1.8436
## gauss:47c87fdfe4a04f4099b 0.3972 2.51733 0.05790 2.7256
## gauss:4828addbdbead772e67 0.4260 2.34717 0.05990 3.0303
## gauss:484bc73b610d95d758e 1.8007 0.55534 0.47987 6.7572
## gauss:4867b892e884fc473bd 4.5868 0.21802 1.02292 20.5675
## gauss:489780c305dbbcdffc6 0.3109 3.21635 0.05064 1.9090
## gauss:48e6351848702136fbe 1.7873 0.55951 0.59612 5.3587
## gauss:498721be13ebb1ca943 0.9698 1.03112 0.07004 13.4291
## gauss:49a2c1264d3155e9ba4 0.9467 1.05635 0.07047 12.7175
## gauss:4a83aa472920431dba7 1.6320 0.61274 0.44165 6.0306
## gauss:4b0e22565eede9b80b8 0.9086 1.10059 0.07103 11.6218
## gauss:4b65c462d4644c44f42 0.7690 1.30035 0.07155 8.2651
## gauss:4b8d6c45f91987c533d 0.5870 1.70355 0.06797 5.0697
## gauss:4bb787d8a1024151089 5.2857 0.18919 1.13839 24.5421
## gauss:4c2743b1059599d0f21 1.8352 0.54489 0.48810 6.9004
## gauss:4c5e1e67ba7a2e18f2a 0.8841 1.13106 0.07131 10.9621
## gauss:4c648e234676d38ddee 0.5644 1.77176 0.06714 4.7447
## gauss:4c9483b6740859d95ff 0.6081 1.64445 0.06866 5.3860
## gauss:4caf5439eaacda7c219 0.9854 1.01481 0.06972 13.9282
## gauss:4cc6a634dd53fa8136f 2.1168 0.47242 0.80037 5.5983
## gauss:4cc911b850d952f2ffe 0.4603 2.17239 0.06206 3.4143
## gauss:4ce78e1eea080f28b2a 0.3900 2.56399 0.05736 2.6519
## gauss:4d3d6d7b9ab8c4db2db 2.8825 0.34693 0.91577 9.0728
## gauss:4d472242ba3106b6801 0.1873 5.33789 0.03583 0.9794
## gauss:4d983b15a5473803ffc 0.7626 1.31136 0.07151 8.1317
## gauss:4e0d1dcafe2e366696a 1.7245 0.57987 0.57500 5.1722
## gauss:4e4e86b06e429142253 1.8310 0.54615 0.60922 5.5031
## gauss:4e7d0f946c1b7f8cfa2 0.6620 1.51064 0.07009 6.2524
## gauss:4ea7046599bf7211d63 0.3638 2.74911 0.05528 2.3936
## gauss:4ed8e2da40dbe4bf833 0.7219 1.38528 0.07112 7.3269
## gauss:4f40f667cdfd4d62e3c 4.0998 0.24392 1.47941 11.3615
## gauss:4f9445c2d11a9878528 0.9553 1.04680 0.07031 12.9788
## gauss:4faabf901d94307622e 0.7125 1.40358 0.07100 7.1497
## gauss:4fc6651227597721d46 8.9733 0.11144 1.65962 48.5173
## gauss:507bc44671664b28ca1 0.9698 1.03112 0.07004 13.4291
## gauss:50a1fcc65af57d9a51b 3.1819 0.31428 1.30282 7.7711
## gauss:50e29aa5c6549f68034 0.7059 1.41657 0.07090 7.0288
## gauss:50f9915c86e606bc5f5 11.7684 0.08497 1.97027 70.2925
## gauss:51820a9292be8584c05 0.7060 1.41636 0.07090 7.0305
## gauss:51ed0df74cd05fbdce9 2.7175 0.36799 0.87121 8.4764
## gauss:5217bebc8e34039d5cd 0.4587 2.17989 0.06197 3.3960
## gauss:5284f13241bdcb5efef 2.1282 0.46989 0.88574 5.1134
## gauss:52926c97eacf158220c 0.9891 1.01104 0.06964 14.0483
## gauss:52cdac423737edc0331 1.0158 0.98443 0.29361 3.5144
## gauss:52db6ac602e29effe7d 0.9131 1.09513 0.07098 11.7478
## gauss:5303df551e77b44fe09 0.6505 1.53722 0.06982 6.0607
## gauss:530e438456d9a3ea91f 0.7566 1.32176 0.07147 8.0092
## gauss:532e1c3acbbd0a0c3e1 1.5568 0.64233 0.42449 5.7098
## gauss:5465dc353f18b140400 0.4326 2.31144 0.06035 3.1016
## gauss:5468384d3a3c27f7161 0.7548 1.32488 0.07146 7.9726
## gauss:54aa6f2cff10123e6fe 0.8012 1.24806 0.07166 8.9586
## gauss:54feddc6e10f2dd7e0b 0.9689 1.03209 0.07006 13.4005
## gauss:557c8090d70c45f6cef 2.8465 0.35130 0.70263 11.5321
## gauss:55c4e5b7212add6da2e 0.9542 1.04798 0.07033 12.9458
## gauss:55ca98ac6131749610f 0.9165 1.09113 0.07093 11.8416
## gauss:55d3b2b90f3a7dc8ccf 0.8536 1.17153 0.07154 10.1843
## gauss:560eed1b046e409ddca 0.8388 1.19212 0.07161 9.8255
## gauss:562c9a18a2647e6758d 0.9487 1.05409 0.07043 12.7783
## gauss:56672b3912be477210d 0.7188 1.39126 0.07108 7.2681
## gauss:5722a6f12c85247a1dc 0.7242 1.38087 0.07115 7.3708
## gauss:57a9ace454c77054db2 6.1775 0.16188 1.27882 29.8409
## gauss:57bd18ab0a985d92f3c 4.5955 0.21761 1.02527 20.5978
## gauss:57d0da5172d067c1d6e 1.2792 0.78176 0.35879 4.5605
## gauss:57d12a1754dfc18a692 0.4164 2.40180 0.05924 2.9263
## gauss:5813b4f44ced8ad6728 1.7716 0.56446 0.58891 5.3294
## gauss:588236e8eea3c3257b7 0.2812 3.55660 0.04752 1.6635
## gauss:591ada137fd09dd634e 0.6774 1.47629 0.07041 6.5168
## gauss:5959aa54e545d7fc405 1.7874 0.55948 0.80117 3.9876
## gauss:5996fa65078b9b01d0b 0.6550 1.52683 0.06993 6.1343
## gauss:59dbb92d52498935862 0.8536 1.17153 0.07154 10.1843
## gauss:59e648a92ea4f233df1 2.7517 0.36341 0.68228 11.0981
## gauss:5b18ea24b6c4b3d22e1 3.7186 0.26892 0.87001 15.8943
## gauss:5b72a10f442b1382f62 0.9342 1.07039 0.07067 12.3501
## gauss:5bb9592cf3fe896be49 0.7985 1.25235 0.07166 8.8980
## gauss:5be1e269132c5db99ff 0.5853 1.70839 0.06791 5.0451
## gauss:5bea7f4faf3ac8cd038 0.9856 1.01466 0.06971 13.9331
## gauss:5bf2fa39816f7eb3735 0.3674 2.72217 0.05556 2.4289
## gauss:5bfb2c9132916fbf0b3 2.6725 0.37419 0.66744 10.7007
## gauss:5c5816712fc99d7314a 0.9136 1.09463 0.07097 11.7596
## gauss:5cbdf86e364c00aecc5 0.7901 1.26568 0.07164 8.7133
## gauss:5cf7e0058df0a8c347b 1.8775 0.53263 0.49739 7.0867
## gauss:5f690fd17a2cc3e926a 1.7190 0.58175 0.46271 6.3859
## gauss:6066e417e1ee13f1e9e 1.4679 0.68122 0.49643 4.3407
## gauss:60e35c3de1b5036bd1c 0.5116 1.95461 0.06483 4.0373
## gauss:60ef075b6761a662b4b 0.9086 1.10059 0.07103 11.6218
## gauss:615020ac1cfaeea3db6 0.7219 1.38528 0.07112 7.3269
## gauss:619e6fe8ed6bb3437b6 0.7701 1.29860 0.07156 8.2870
## gauss:61f8d7d3586ae32cf69 0.7440 1.34416 0.07136 7.7560
## gauss:62016e8b373a61c2fa0 0.6136 1.62975 0.06883 5.4699
## gauss:621fca8e45b08c156a0 0.3053 3.27582 0.09879 0.9433
## gauss:628ecc8fbdb764f1361 0.8046 1.24291 0.07167 9.0323
## gauss:62d4ffaa0db7ce973d9 2.3380 0.42772 0.75773 7.2139
## gauss:630e3e9d4fbb58d3cd7 0.6227 1.60589 0.28542 1.3586
## gauss:6390814bd89f8f5a0ab 0.9431 1.06036 0.07053 12.6105
## gauss:63bede1e09caeb1bb24 0.6623 1.50984 0.07010 6.2581
## gauss:64606a449d86b7f992d 0.8637 1.15783 0.07148 10.4359
## gauss:64746751824dd14c842 0.6596 1.51610 0.07004 6.2119
## gauss:648de3ab05c1187dc50 4.0798 0.24511 0.93442 17.8131
## gauss:64e87bb4ce4690135c9 0.4380 2.28331 0.13176 1.4557
## gauss:6541686d13d1089f40f 0.7805 1.28124 0.07161 8.5071
## gauss:6564c40c23b18c43dc2 0.9829 1.01744 0.06977 13.8457
## gauss:65bc38739e9935d1b9e 0.6704 1.49160 0.07027 6.3967
## gauss:65cd9844ce768e70808 4.8926 0.20439 1.07448 22.2780
## gauss:6644c693b212aa59059 0.6352 1.57436 0.06944 5.8102
## gauss:664b2399064a0376d40 0.7164 1.39583 0.07105 7.2239
## gauss:66e5706b550af598f9d 0.7446 1.34306 0.07137 7.7677
## gauss:66f554f5e7b3faeb63c 0.8488 1.17812 0.07157 10.0670
## gauss:670e2de3622b2fd06ce 2.1717 0.46046 0.81774 5.7677
## gauss:672e834f78a35afcbac 0.9979 1.00208 0.06944 14.3418
## gauss:67ca54c3f85b471a5f6 0.9023 1.10829 0.07111 11.4485
## gauss:67da36022555d710da6 3.2450 0.30816 0.78033 13.4947
## gauss:6811313aa5af08c1389 4.2441 0.23562 1.53089 11.7662
## gauss:6812cdcccc89fb80e4a 0.2497 4.00489 0.08654 0.7204
## gauss:681b23726076f4e00b8 0.5073 1.97105 0.06462 3.9831
## gauss:6882e0ff44d4d753cde 0.5991 1.66904 0.06838 5.2498
## gauss:68fc7a7323283aa9720 0.8524 1.17320 0.07155 10.1541
## gauss:696098786b0348586a6 5.7577 0.17368 1.21372 27.3133
## gauss:69640a2e7b2b2fbb5ba 2.1248 0.47064 0.55180 8.1815
## gauss:696ebb2d6d3c39fdd28 0.7350 1.36063 0.07127 7.5789
## gauss:69d7253fcf3ba339860 0.8256 1.21122 0.07165 9.5130
## gauss:69e02f110a0357878ad 2.2980 0.43516 0.86420 6.1108
## gauss:6a66b3334f22644369b 0.8581 1.16540 0.07152 10.2955
## gauss:6a7433c7e7bc7be9d93 0.9828 1.01753 0.06977 13.8427
## gauss:6aa5efce979a49e20e3 0.8272 1.20890 0.07165 9.5502
## gauss:6aae55039094e412d07 1.5039 0.66495 0.50815 4.4507
## gauss:6af5e04b93d9840308a 1.8137 0.55135 0.48381 6.7993
## gauss:6b10d4288a0188ca0e2 0.3537 2.82687 0.05448 2.2969
## gauss:6b2e532feefb2bddb08 0.8155 1.22627 0.07167 9.2790
## gauss:6b4eb22bce2d8c35a5f 0.9546 1.04758 0.07033 12.9569
## gauss:6b52f88d560079a9297 0.5538 1.80585 0.06671 4.5964
## gauss:6b6637e744ee3ecc4c5 0.9979 1.00208 0.06944 14.3418
## gauss:6b7f10ad465f16a8161 0.9394 1.06446 0.07059 12.5029
## gauss:6beaba352c02e2f2430 0.6748 1.48182 0.07036 6.4731
## gauss:6c028804bd39f3f4d0a 0.7180 1.39277 0.07107 7.2534
## gauss:6c6d6e9c19938267d1f 0.6874 1.45482 0.07059 6.6930
## gauss:6c8870fe6e85b08ad44 0.5706 1.75266 0.17570 1.8529
## gauss:6cecd23ba8083d17f94 0.8221 1.21645 0.07166 9.4311
## gauss:6d1569546dd68044af9 0.5459 1.83195 0.06639 4.4882
## gauss:6d5cb27f7d7e2b5bec4 0.4985 2.00598 0.06418 3.8723
## gauss:6d67a23a83ad9f81759 5.3690 0.18625 1.59056 18.1236
## gauss:6d78807f545ad19271f 10.5705 0.09460 4.03605 27.6842
## gauss:6d88d4645f52c3d0a91 1.6754 0.59686 0.45287 6.1985
## gauss:6d9239e2aa02f0b7941 0.2256 4.43213 0.04117 1.2364
## gauss:6de021e28d21127903d 7.7745 0.12863 1.50534 40.1519
## gauss:6def631f920c4c16312 0.7626 1.31136 0.07151 8.1317
## gauss:6df94922b2a0767682e 0.8056 1.24134 0.07167 9.0555
## gauss:6e6356c4ae3d2028a08 0.8543 1.17057 0.07154 10.2013
## gauss:6e7d1d439891ccace88 0.4666 2.14303 0.06243 3.4877
## gauss:6f3982a7c01fcb27daf 1.3019 0.76813 0.36492 4.6445
## gauss:6f82c318ea90ea0a948 0.4586 2.18055 0.06196 3.3944
## gauss:709ae4607d31cdd3a29 0.3674 2.72217 0.05556 2.4289
## gauss:709f8a273f06704de01 0.8427 1.18659 0.07160 9.9196
## gauss:70d1d00d05b37bc94a2 6.8296 0.14642 1.96570 23.7290
## gauss:70d6a62ab3778aec6a9 0.3360 2.97578 0.05295 2.1326
## gauss:70e5205489dba974b22 0.4407 2.26905 0.06087 3.1909
## gauss:711d649901aaca4356c 0.3799 2.63219 0.11986 1.2042
## gauss:71461848e5b67b9502e 1.7855 0.56007 0.59545 5.3539
## gauss:71541652926566c856f 0.4276 2.33883 0.06000 3.0468
## gauss:71f1d14d4e85f39ae21 0.7027 1.42299 0.07085 6.9704
## gauss:720399b6a401897bfba 2.3966 0.41727 0.61038 9.4097
## gauss:726255ccb5bc914670c 3.6103 0.27698 0.84971 15.3398
## gauss:731714fe3883219c9cc 0.2631 3.80060 0.04573 1.5140
## gauss:73336e1c6ccf83ef58f 0.3030 3.30002 0.04981 1.8436
## gauss:7452e138032751d84c2 6.5215 0.15334 1.88797 22.5268
## gauss:74c193edef9c7e71faf 0.9948 1.00521 0.06951 14.2379
## gauss:74c385e288a7a27fadb 0.6739 1.48396 0.07034 6.4560
## gauss:74fd76b6ded5a19c8ff 0.6961 1.43655 0.07075 6.8495
## gauss:7504cce056591e8015c 0.9363 1.06801 0.07064 12.4112
## gauss:759bb1cc0dbe203e51d 0.5970 1.67501 0.06831 5.2179
## gauss:75f0049bf47aa9eb4df 0.8151 1.22690 0.07167 9.2697
## gauss:760db515eb93efe5b0a 0.7990 1.25151 0.07166 8.9096
## gauss:76eab6eca0ae90f4bf6 0.6250 1.59998 0.06916 5.6481
## gauss:76f36903b18e412d809 3.6802 0.27173 1.79009 7.5658
## gauss:7735525016452e6a191 0.9731 1.02764 0.06997 13.5327
## gauss:775f8096030c1f878a5 0.5005 1.99793 0.06428 3.8975
## gauss:78765680fc4f009e36d 0.4260 2.34717 0.05990 3.0303
## gauss:789cefe30b1d4adc2ab 0.8587 1.16455 0.07151 10.3111
## gauss:78cb462afe695223ca4 6.9623 0.14363 1.39379 34.7777
## gauss:7929fa319919605f6fd 0.6686 1.49573 0.07023 6.3646
## gauss:7995cee8ed0a7dc1865 0.4024 2.48513 0.05827 2.7787
## gauss:799b9a668a1e0725245 0.9838 1.01644 0.06975 13.8769
## gauss:79beab38202ff5516aa 0.7373 1.35623 0.07129 7.6258
## gauss:7a63566290f56120244 0.8775 1.13954 0.07137 10.7908
## gauss:7a7ae00d24b5c2779c1 0.4853 2.06065 0.06348 3.7098
## gauss:7acae419292ad488c5e 0.5748 1.73984 0.06753 4.8919
## gauss:7b1b7babaddee3b4308 0.7736 1.29266 0.07157 8.3613
## gauss:7b29ad0abd97370a5b5 0.5239 1.90891 0.06541 4.1953
## gauss:7b98dafbe7b67231a64 0.4653 2.14915 0.06235 3.4722
## gauss:7bb7a0ffbb3b592eda4 0.9371 1.06714 0.07063 12.4336
## gauss:7bed6c8c955b3c5d0a8 1.6417 0.60911 0.44398 6.0708
## gauss:7c3e1a2aa5110392be0 0.9897 1.01040 0.06962 14.0690
## gauss:7da4979ed4f36cfd59d 0.8243 1.21319 0.07166 9.4817
## gauss:7dce4702ad6404cd1ee 1.7342 0.57665 0.57807 5.2024
## gauss:7dd2eeba9fb5b763747 0.6894 1.45058 0.07063 6.7286
## gauss:7e28fc37e217fbab73e 0.9502 1.05244 0.07040 12.8235
## gauss:7ead68bf9eb6d118c9a 4.7405 0.21095 2.19787 10.2245
## gauss:7edb1666620f3bece30 0.4276 2.33883 0.06000 3.0468
## gauss:7ee6bd20aad6b4a05a0 0.4034 2.47864 0.05833 2.7905
## gauss:7f500c7092091b41f02 0.2525 3.96093 0.04453 1.4313
## gauss:7fbf0dbb7e98bd0fa8a 2.2419 0.44605 0.57677 8.7144
## gauss:7fc24f6d3a8cbff352f 0.8413 1.18870 0.07160 9.8837
## gauss:7fccb815a0221c7da09 0.8841 1.13106 0.07131 10.9621
## gauss:7fe45332d05027388e7 0.6868 1.45595 0.07059 6.6833
## gauss:7ff0e2c9a141f284e92 0.8504 1.17585 0.07156 10.1070
## gauss:8046f59021fad41c087 4.4259 0.22594 0.99491 19.6889
## gauss:80cbb2794ca19c0931f 0.8488 1.17812 0.07157 10.0670
## gauss:80d0f6e08d266c23d4d 0.5339 1.87313 0.06587 4.3270
## gauss:8140f5c61cbe8d65b95 0.5376 1.86025 0.06603 4.3761
## gauss:815b3894d0bbc761130 0.9689 1.03209 0.07006 13.4005
## gauss:8174a768a8bef0f5059 2.2461 0.44522 0.73290 6.8835
## gauss:81ca2fe6d952d2499ae 0.5570 1.79536 0.06685 4.6410
## gauss:81ee5ea98ef1fb80ad1 0.3819 2.61834 0.05672 2.5715
## gauss:82096c55345c15c9652 0.7489 1.33522 0.07141 7.8552
## gauss:821519a1d33a03eedeb 3.1841 0.31406 0.76800 13.2009
## gauss:82e776974cb94e9de19 0.3298 3.03225 0.05232 2.0787
## gauss:833424159ac725fae73 5.9235 0.16882 1.73466 20.2274
## gauss:83cf20f8479d20af557 0.2958 3.38061 0.04904 1.7841
## gauss:8417f8bd46670b8d1c6 0.7746 1.29092 0.07158 8.3828
## gauss:841865e67487488ffc6 2.7636 0.36185 1.02475 7.4529
## gauss:8537ab54d899619a0c6 3.0847 0.32418 0.97315 9.7782
## gauss:85a137ae41861234a42 0.9527 1.04963 0.07036 12.9002
## gauss:85bb98c4b3b4153449b 0.6175 1.61948 0.06895 5.5301
## gauss:8603873bc173f89adb7 0.5239 1.90891 0.06541 4.1953
## gauss:861df31eae2e1c05f0b 0.8830 1.13249 0.07132 10.9328
## gauss:862ba530cf2a21c06c9 0.3761 2.65865 0.05627 2.5141
## gauss:86573557a1c4d0ee2fd 0.3439 2.90806 0.05358 2.2069
## gauss:86635b4a6f512e48e68 0.7550 1.32447 0.07146 7.9776
## gauss:86742d5de56681cae47 0.8172 1.22364 0.07166 9.3193
## gauss:869399b9e14f68ed3ff 0.8556 1.16875 0.07153 10.2344
## gauss:86942daa24f0e6a76df 0.5527 1.80933 0.06667 4.5816
## gauss:86bb162732ad241cac6 3.7489 0.26674 0.87547 16.0536
## gauss:86dfcd6df1f361bdae4 0.5970 1.67501 0.06831 5.2179
## gauss:878d7f8429924562d4a 0.4068 2.45812 0.05857 2.8256
## gauss:87f7a64ae1c6e55c91d 1.7976 0.55630 0.47934 6.7412
## gauss:8825c6ff667ccd31695 1.6717 0.59820 0.69833 4.0017
## gauss:8888913667940fea2b7 0.5327 1.87724 0.06582 4.3114
## gauss:888ff7a390863729394 0.5125 1.95107 0.06488 4.0491
## gauss:88ad7f228f444ef121a 3.2523 0.30747 0.78129 13.5386
## gauss:8917a67e740676aa327 27.7567 0.03603 8.37764 91.9628
## gauss:89263c34dfcfdb28246 0.7138 1.40095 0.07101 7.1749
## gauss:895d1225866e6ff9d40 0.6926 1.44382 0.07068 6.7866
## gauss:89868e059740330fdb8 0.6756 1.48010 0.07037 6.4865
## gauss:89cad0e0796da83b8df 0.9974 1.00260 0.06945 14.3245
## gauss:8a0ef7a4566bb8775f6 0.2538 3.94069 0.04455 1.4453
## gauss:8a20463b73bfeec5ba4 0.6198 1.61347 0.06901 5.5661
## gauss:8a20ca73797dbe6e885 11.2679 0.08875 1.91886 66.1668
## gauss:8a6525ed2cc686e2ab0 0.9080 1.10136 0.07104 11.6046
## gauss:8a904e7336d62c9d759 0.8364 1.19562 0.07162 9.7671
## gauss:8ae8cb1cfb8525c926a 0.6541 1.52890 0.06991 6.1194
## gauss:8af08d0756c05d0d244 8.4566 0.11825 1.59522 44.8300
## gauss:8af7f2c82355a164c57 0.4745 2.10755 0.06288 3.5804
## gauss:8cc5965f43c98d62df5 0.8753 1.14249 0.07139 10.7318
## gauss:8d071c2aaad9f14829c 0.2803 3.56769 0.04748 1.6546
## gauss:8d1edc9376ebc47a382 0.3883 2.57534 0.05723 2.6344
## gauss:8d6238611f168bea8fe 0.3127 3.19791 0.05075 1.9268
## gauss:8d6c8539a4963ae3324 3.1975 0.31275 1.17309 8.7152
## gauss:8df6ee9fc39eed04d79 5.0400 0.19841 1.50805 16.8440
## gauss:8eafc5be8aa452c8e81 0.8100 1.23459 0.07167 9.1544
## gauss:8eaffa60fc54d19ddeb 0.8762 1.14128 0.07138 10.7558
## gauss:8ec618e87026cb06b90 0.7879 1.26916 0.07163 8.6666
## gauss:8fdb2a2cc03093c6069 0.9582 1.04363 0.07026 13.0674
## gauss:9042758ae8919bdb6cf 0.5111 1.95644 0.06481 4.0313
## gauss:90438600c56885f0f1f 0.7914 1.26355 0.07164 8.7427
## gauss:9094d930784487cb727 0.2026 4.93576 0.03845 1.0675
## gauss:91845e4de7c1c9fab56 4.9579 0.20170 1.48193 16.5873
## gauss:919f336f95e51d0e918 0.5549 1.80229 0.06676 4.6114
## gauss:91abbf93e91d64fd01e 0.3947 2.53339 0.05769 2.7007
## gauss:91be80304f7794f5541 0.7141 1.40046 0.07102 7.1794
## gauss:91c5f1b698b64301bd8 0.9528 1.04949 0.07036 12.9041
## gauss:924ad98ddbb2703cce9 0.5073 1.97105 0.06462 3.9831
## gauss:925e3728ea5d50c8aed 0.6800 1.47064 0.07046 6.5623
## gauss:928b073a7c2affa7a75 3.4327 0.29132 1.50882 7.8097
## gauss:92c0905e52d850dd121 1.3775 0.72596 0.38209 4.9661
## gauss:942cb5b5e5b99c8a697 2.5270 0.39573 0.63651 10.0322
## gauss:944bd0001a06adb1227 0.9451 1.05805 0.07049 12.6718
## gauss:946ec79d6eccedfdbe2 0.3807 2.62697 0.05662 2.5594
## gauss:947dac42da87efa6a25 0.3451 2.89799 0.05374 2.2157
## gauss:94908001b9dfc358aab 1.4447 0.69219 0.60725 3.4370
## gauss:94a2c55bd2fc7a408b5 0.3138 3.18701 0.05091 1.9339
## gauss:94cb854a8da3259a733 1.1457 0.87285 0.32577 4.0291
## gauss:94d8e4f9939e9caf326 2.9332 0.34093 0.71837 11.9764
## gauss:94df258944fa6ff3bd4 0.8830 1.13249 0.07132 10.9328
## gauss:952b1e2cff75915daa9 9.7880 0.10217 2.66547 35.9433
## gauss:952b2e28f4b32a9230a 0.3807 2.62697 0.05662 2.5594
## gauss:953a8fa1bd61d1a8c44 1.9746 0.50642 0.52003 7.4979
## gauss:95460d4ddaa3530522d 0.9774 1.02313 0.06989 13.6694
## gauss:954ab7567bef9f75920 0.5290 1.89027 0.06565 4.2628
## gauss:955d20a844f9985afa5 1.8868 0.52999 0.62436 5.7019
## gauss:96147caf0eed5bcec9d 11.7908 0.08481 3.12659 44.4650
## gauss:961da3ed80e07f0911a 0.5484 1.82361 0.06649 4.5223
## gauss:96638942bba19c48f6d 0.8830 1.13249 0.07132 10.9328
## gauss:966c215dffee84c1ff1 0.8762 1.14128 0.07138 10.7558
## gauss:96afb35fa7e7ee5dd39 0.8556 1.16883 0.07153 10.2328
## gauss:97261c07880b9532b7f 2.0990 0.47643 0.54620 8.0660
## gauss:972c4cbb58f8b338366 1.3323 0.75057 0.45360 3.9133
## gauss:9738815164e23a98b97 7.3122 0.13676 2.07999 25.7058
## gauss:97617d5cfcfccd30995 0.8753 1.14249 0.07139 10.7318
## gauss:978e1405a7797c5c999 6.4927 0.15402 1.88181 22.4015
## gauss:978fad77b59a27d456d 0.3405 2.93673 0.05329 2.1760
## gauss:985cf029363df029cdd 0.8846 1.13052 0.07130 10.9737
## gauss:98af7d4e9db2616056c 0.5169 1.93448 0.06509 4.1056
## gauss:98bc3fa9bc5c67ba6ca 1.6689 0.59921 0.45085 6.1774
## gauss:992c57e25d3bd5efbc4 0.9446 1.05863 0.07050 12.6565
## gauss:994cccba18f9ebb1c77 3.0414 0.32879 0.74033 12.4948
## gauss:99e95551b8e486ce04b 6.2778 0.15929 1.82266 21.6227
## gauss:99eb20b7347f1b1891a 0.5051 1.97989 0.06451 3.9545
## gauss:9a1cd818c0284a166fb 0.7115 1.40549 0.07098 7.1320
## gauss:9ad3b8a9b1c70b21353 0.6215 1.60906 0.06906 5.5925
## gauss:9aea1de2dd86b2efe46 0.4258 2.34827 0.13001 1.3948
## gauss:9afd58adbf9022472c5 0.6713 1.48963 0.07028 6.4119
## gauss:9b06e6eb9905d3167e7 17.0527 0.05864 6.28537 46.2654
## gauss:9bb0474450e88655911 0.8745 1.14352 0.07139 10.7117
## gauss:9bccb8fc27a9eeaa44b 0.5930 1.68625 0.06818 5.1586
## gauss:9be69d91a00fb1484b8 0.9806 1.01980 0.06982 13.7721
## gauss:9c2d8658bc7ced277db 3.6321 0.27532 0.85399 15.4477
## gauss:9c2dcca1649b78e4fa4 0.3997 2.50186 0.05805 2.7520
## gauss:9c3cadc1e1766adba7c 0.9546 1.04758 0.07033 12.9569
## gauss:9c848567c8c0000bd3b 0.9191 1.08806 0.07090 11.9145
## gauss:9cd075508de926a73f0 2.8127 0.35553 0.89593 8.8305
## gauss:9d0ff9cab085952233f 8.2119 0.12177 1.56092 43.2023
## gauss:9d13f7974119875c688 8.3095 0.12034 2.32378 29.7135
## gauss:9d1cd873f3fbd0993fa 6.2536 0.15991 1.29062 30.3009
## gauss:9d22df349951c4b0889 0.6783 1.47436 0.07042 6.5325
## gauss:9d49a30d5723647bb6e 0.3728 2.68243 0.05600 2.4818
## gauss:9d6ac643f16e294fa22 0.6494 1.53983 0.06980 6.0423
## gauss:9d99e84abe82fa13811 0.5152 1.94109 0.06501 4.0828
## gauss:9d9d24fdfa92dbbf780 8.8509 0.11298 1.64309 47.6771
## gauss:9de8e4cc69056bd4b94 0.5086 1.96623 0.06469 3.9986
## gauss:9deef0191942bff7c79 0.3947 2.53339 0.05769 2.7007
## gauss:9e97a3ae46d97e32e34 1.9719 0.50713 0.51839 7.5008
## gauss:9ea209112e53fa62bea 0.9114 1.09716 0.07100 11.7007
## gauss:9f0036d362f4c8c2b41 0.5818 1.71882 0.06779 4.9933
## gauss:9f1fb96b08b575b36f5 1.1287 0.88600 0.32181 3.9585
## gauss:9f7bfd2287392e9c125 0.5655 1.76847 0.06718 4.7595
## gauss:9f816dd1d6ec8d06920 0.8172 1.22364 0.07166 9.3193
## gauss:a00d11bafc94d2db757 0.9592 1.04256 0.07024 13.0978
## gauss:a057ad50bab39207fa8 0.8151 1.22690 0.07167 9.2697
## gauss:a0a384adfdde4385336 0.7845 1.27469 0.07162 8.5926
## gauss:a0ab2a18c362bf4954b 9.0618 0.11035 3.06554 26.7866
## gauss:a0f0bedfd369e708be4 0.9394 1.06446 0.07059 12.5029
## gauss:a1456dd561f8e14f39c 0.9451 1.05805 0.07049 12.6718
## gauss:a1749464664e2cc948e 0.9279 1.07769 0.07077 12.1667
## gauss:a1b6293786d17d520ab 0.8801 1.13629 0.07135 10.8555
## gauss:a1e8fc44d489bfa5eeb 0.9034 1.10689 0.07110 11.4797
## gauss:a22ebaad23dfc6dd00a 1.0387 0.96273 0.36235 2.9775
## gauss:a24ce7ed89dfd33e2b2 0.6541 1.52890 0.06991 6.1194
## gauss:a285dd2e565548050da 0.7379 1.35521 0.07131 7.6360
## gauss:a2e7d3a72803ed5c967 0.6523 1.53303 0.06987 6.0902
## gauss:a32655223a671c00160 0.5644 1.77176 0.06714 4.7447
## gauss:a34819a7d2b48733870 0.7562 1.32236 0.07147 8.0018
## gauss:a3539f36d311b631a07 1.9147 0.52227 0.50667 7.2358
## gauss:a3a3f17221c7626564f 0.7446 1.34306 0.07137 7.7677
## gauss:a3aa22d8991e4d41346 6.3358 0.15783 1.30216 30.8272
## gauss:a3d30d742f6a9a6f4e3 0.6523 1.53303 0.06987 6.0902
## gauss:a4359cfcff6b6be645a 0.8498 1.17673 0.07156 10.0913
## gauss:a493f0aefe6c0d7c417 0.8415 1.18842 0.07160 9.8884
## gauss:a4e895118e18c6238bf 0.9086 1.10059 0.07103 11.6218
## gauss:a525608cbcdbd9d35c3 0.8637 1.15783 0.07148 10.4359
## gauss:a52db76bf1aa9d5f7e6 0.7241 1.38099 0.07115 7.3700
## gauss:a53fcbad2258a004932 4.8032 0.20819 1.05962 21.7729
## gauss:a53fddcfcb734935478 0.7843 1.27499 0.07162 8.5892
## gauss:a58049b478c25be9491 0.9418 1.06180 0.07055 12.5726
## gauss:a5afab74e932b2ee546 0.9191 1.08806 0.07090 11.9145
## gauss:a6588faa139f9c39644 0.3838 2.60563 0.05687 2.5901
## gauss:a67dc18e8d52f092686 4.1286 0.24221 1.26181 13.5086
## gauss:a6d346ab3c6bd8f30ca 0.7349 1.36076 0.07127 7.5772
## gauss:a7292b77e904ecf8bc5 0.8064 1.24015 0.07167 9.0726
## gauss:a743a9a726623fd8f5c 0.4296 2.32761 0.06014 3.0693
## gauss:a76a23676e7dededf37 0.9131 1.09513 0.07098 11.7478
## gauss:a78eec6f0a522887250 1.1994 0.83377 0.41076 3.5020
## gauss:a7d9ac101685ed59e14 0.9511 1.05141 0.07039 12.8515
## gauss:a7fc88b039bdc3c1706 0.5971 1.67488 0.06831 5.2184
## gauss:a896695e035aeda9594 7.3078 0.13684 1.44237 37.0253
## gauss:a89a934ffb29bec688b 8.4293 0.11863 2.35348 30.1908
## gauss:a925650871d114301d5 10.7906 0.09267 1.86908 62.2967
## gauss:a9401685893254ff6f5 0.5591 1.78852 0.06693 4.6707
## gauss:a9702d020f3395e4b3d 0.5928 1.68679 0.06817 5.1556
## gauss:a999e05fd781a5ef18d 4.2549 0.23503 0.96527 18.7553
## gauss:a9a19800879c12826e4 0.8073 1.23869 0.07167 9.0937
## gauss:a9d9b41ae63fde9b405 1.2360 0.80905 0.42362 3.6064
## gauss:aa3b3390eacc9aea36b 0.9587 1.04309 0.07025 13.0826
## gauss:aaec2a893559c33779c 0.2812 3.55660 0.04752 1.6635
## gauss:aaf9ffd9387578b5ddd 0.4732 2.11328 0.06281 3.5651
## gauss:ab2c1b78c4404a78f32 0.9335 1.07125 0.32637 2.6699
## gauss:ac14f1f9fefe307bc41 0.8536 1.17153 0.07154 10.1843
## gauss:ac295de51e46b5b5b12 0.3473 2.87948 0.05393 2.2363
## gauss:ac59352cfd955ba9b3e 0.9769 1.02366 0.06990 13.6532
## gauss:ac9a72f833ecc2bbdb1 0.8388 1.19212 0.07161 9.8255
## gauss:acb42655c1dd8baf6dd 0.3214 3.11165 0.05157 2.0027
## gauss:ad06f96452538f74d9a 0.8263 1.21024 0.07165 9.5286
## gauss:ad2a76a3ba6a633a073 0.6800 1.47064 0.07046 6.5623
## gauss:ad40f72531b894a011b 0.5135 1.94758 0.06492 4.0609
## gauss:adaa1199028825f95db 0.8073 1.23869 0.07167 9.0937
## gauss:adb2abc1d5185cf7fdc 0.4672 2.14028 0.17000 1.2842
## gauss:ade990c038993e273f2 0.2994 3.34010 0.04945 1.8128
## gauss:adf0000082ceca13d36 0.3219 3.10681 0.05159 2.0083
## gauss:adf3dccfa6b3c7d863f 0.9822 1.01808 0.06978 13.8257
## gauss:ae077c98e9ecdcdcd2e 0.9251 1.08096 0.07081 12.0863
## gauss:ae377bf226d3e784a93 0.1190 8.40094 0.02559 0.5538
## gauss:ae58ad7a1dafa917ce1 0.9459 1.05721 0.07048 12.6944
## gauss:ae6f89772166092fbe2 6.9499 0.14389 1.39041 34.7386
## gauss:af07cf098e0bec5a317 6.7506 0.14814 1.94396 23.4421
## gauss:af1894983f416210c4b 0.7109 1.40674 0.07097 7.1200
## gauss:af7f42862ce19ae503a 0.6894 1.45058 0.07063 6.7286
## gauss:af88a75af88a50c7dca 0.8547 1.16997 0.07153 10.2129
## gauss:af9b857ee2fcc7269de 2.9145 0.34311 0.71501 11.8800
## gauss:b069d4856c06b7e29ad 0.5100 1.96092 0.06475 4.0164
## gauss:b0b2b1ccac910ee3811 2.6396 0.37884 0.84551 8.2407
## gauss:b10a4d5701abade8fb8 2.1349 0.46841 0.55359 8.2329
## gauss:b186b243a7693de3f91 0.3470 2.88188 0.05385 2.2358
## gauss:b1abb761374e8d77898 9.6346 0.10379 2.63980 35.1642
## gauss:b1b05386ebd18251bef 0.9974 1.00260 0.06945 14.3245
## gauss:b1b97a054f7444848db 1.2297 0.81322 0.34667 4.3619
## gauss:b1c2fe0c890336ae116 4.0505 0.24688 1.24051 13.2257
## gauss:b282a57d611b3934cbb 0.4586 2.18055 0.06196 3.3944
## gauss:b31e4bfbd95b43c6696 0.4472 2.23605 0.06127 3.2645
## gauss:b348f084c2e4d848a30 0.4952 2.01955 0.06400 3.8308
## gauss:b444ff359ca3628b4fe 0.9783 1.02218 0.06987 13.6987
## gauss:b48374276414701798d 0.6802 1.47025 0.07046 6.5658
## gauss:b4b4905bfa957066c86 1.0555 0.94743 0.36659 3.0390
## gauss:b4cd19926c25adcef0b 0.8543 1.17057 0.07154 10.2013
## gauss:b4d7a97236d6f84aa7f 1.8903 0.52902 0.49997 7.1469
## gauss:b539dec486473eb8af9 3.2188 0.31067 1.18511 8.7425
## gauss:b54f3750cf4b1fe8636 0.7656 1.30622 0.07153 8.1937
## gauss:b566e92028af2f32d9e 7.0301 0.14224 2.01225 24.5609
## gauss:b57418e3d3437929bb2 0.2436 4.10558 0.04328 1.3709
## gauss:b5a46ebf3b2c3bedf05 0.3570 2.80098 0.05472 2.3293
## gauss:b5cc258f589daec3bc2 0.8415 1.18842 0.07160 9.8884
## gauss:b5cd8e708107754a633 4.4092 0.22680 1.58127 12.2945
## gauss:b5e71b13c29f7262092 7.9654 0.12554 1.53143 41.4306
## gauss:b6304e1300c0d46f008 0.9185 1.08870 0.07090 11.8993
## gauss:b6f1c897656f26660d6 0.6269 1.59519 0.06921 5.6778
## gauss:b727500fab12f701283 0.7519 1.32998 0.07143 7.9141
## gauss:b744fbad1721f969d8c 0.8151 1.22690 0.07167 9.2697
## gauss:b764845a392085d3ff5 0.9341 1.07053 0.07067 12.3468
## gauss:b76f2724998317374fe 0.6407 1.56090 0.06958 5.8988
## gauss:b781f927da896a23be5 1.3920 0.71841 0.38573 5.0232
## gauss:b7b37f2cab4b04341ec 1.1168 0.89541 0.31872 3.9133
## gauss:b7f03c1a22d79551356 0.7577 1.31985 0.07148 8.0310
## gauss:b894599b34a711b5e9a 0.6546 1.52767 0.06991 6.1288
## gauss:b90fe31086110006143 0.2994 3.34010 0.04945 1.8128
## gauss:b930696f424fc16f55e 0.3402 2.93960 0.05328 2.1722
## gauss:b985d2e2242011017fe 0.4103 2.43701 0.05882 2.8627
## gauss:b994df9a932b410b21f 0.6193 1.61467 0.06900 5.5590
## gauss:ba4ccfb48d84cba1d52 2.9261 0.34175 0.93006 9.2059
## gauss:ba97c01fb98e03d2f91 0.7138 1.40095 0.07101 7.1749
## gauss:bae26bc2c87f1ca969a 1.6372 0.61078 0.74021 3.6213
## gauss:bb6259d564451d67bb1 2.7124 0.36868 0.67441 10.9089
## gauss:bbc94373434508929db 0.9693 1.03169 0.33796 2.7800
## gauss:bc111f60365b63d51c6 16.8142 0.05947 4.19017 67.4715
## gauss:bc6b812c3f7ec034cc5 0.2042 4.89599 0.03839 1.0868
## gauss:bc96087c2003361b9bb 0.2538 3.94069 0.04455 1.4453
## gauss:bccf3f7e79fd6fafeef 0.7431 1.34573 0.07136 7.7384
## gauss:bd1bd50d177586724ed 0.8735 1.14485 0.07140 10.6852
## gauss:bd9479fd60f556a1019 5.2549 0.19030 1.13361 24.3590
## gauss:bde967ce7aa84ae4c87 0.9424 1.06114 0.07054 12.5901
## gauss:bdeeeb0f1ce7fc1259a 2.4129 0.41444 0.90474 6.4351
## gauss:bdf3dd63c5a5af0a929 0.3030 3.30002 0.04981 1.8436
## gauss:be115b23021b1bcff7f 5.2086 0.19199 1.12660 24.0810
## gauss:be1d4ab9f70f11b475c 0.6849 1.46004 0.07055 6.6494
## gauss:be67d631e949e14c344 0.5181 1.93016 0.06514 4.1205
## gauss:be85f3a99c5c043fefa 0.9838 1.01644 0.06975 13.8769
## gauss:bef0c0b5fe52f9579ff 0.8624 1.15949 0.07149 10.4048
## gauss:bf037e7508dcef9bbba 0.6698 1.49304 0.07025 6.3854
## gauss:bf7900e7df77a423ba5 0.2099 4.76325 0.03941 1.1184
## gauss:bf810f64975849c562b 0.2844 3.51639 0.04800 1.6848
## gauss:bfa98550b758cdd5bac 0.6833 1.46357 0.07052 6.6202
## gauss:bfadb4d175c83ad4522 0.7626 1.31136 0.07151 8.1317
## gauss:bfb64ca4f01e4da3fb5 3.0259 0.33048 0.73724 12.4194
## gauss:c00c9a94c5666b4906c 0.4118 2.42855 0.05892 2.8776
## gauss:c0ca6f0f6b2ad8e61f9 0.4600 2.17414 0.06204 3.4100
## gauss:c0fd2c7cc523ec63e3b 0.4811 2.07843 0.06325 3.6598
## gauss:c0fef89af6dd171b5c2 0.2767 3.61386 0.04719 1.6224
## gauss:c0ff51276486d9382a9 0.7036 1.42132 0.07087 6.9852
## gauss:c11151a96bad94d6f67 5.9518 0.16802 2.08949 16.9533
## gauss:c12e3b8c6786704dc03 6.3317 0.15794 1.30034 30.8308
## gauss:c14b81f18b27f05fc9c 0.6703 1.49177 0.07027 6.3951
## gauss:c158fc6f61c44fea323 0.9219 1.08475 0.07085 11.9942
## gauss:c16b83a3dbdeee6989a 0.9005 1.11043 0.07113 11.4010
## gauss:c16f94ed7c5b1d9c8fb 0.6019 1.66130 0.06847 5.2920
## gauss:c18b3be59720862c1f5 0.6936 1.44177 0.07070 6.8041
## gauss:c1dc6f0ebcd353c916e 5.0532 0.19789 1.80166 14.1730
## gauss:c215c73076040b3cb7b 0.7605 1.31490 0.07150 8.0894
## gauss:c276a126280a9fa0d83 0.6712 1.48981 0.07029 6.4103
## gauss:c28477d08ff49da4777 7.4661 0.13394 1.46277 38.1076
## gauss:c2a2997be9343592995 0.9086 1.10059 0.07103 11.6218
## gauss:c2e14cc02c43ba67f72 0.4230 2.36423 0.05969 2.9970
## gauss:c2e5c79a5abef93d0d5 0.4626 2.16149 0.06220 3.4412
## gauss:c2ed279d41c0eaab65e 0.9991 1.00089 0.34785 2.8697
## gauss:c2f60f17ff5f9daa6c3 1.5617 0.64033 0.42513 5.7367
## gauss:c38eacb47d516c7e6b2 2.6722 0.37422 0.66714 10.7035
## gauss:c3b15bf1c00be31edd3 0.9979 1.00208 0.06944 14.3418
## gauss:c3db97bc572efa7c67b 0.7141 1.40046 0.07102 7.1794
## gauss:c4b3e757c239deb3107 0.3030 3.30002 0.04981 1.8436
## gauss:c4d3a99600c482cdc51 5.3808 0.18585 1.15433 25.0820
## gauss:c4e108bf008408bd0ca 0.6496 1.53933 0.06980 6.0460
## gauss:c53e6cc568d87321249 0.9488 1.05397 0.07043 12.7816
## gauss:c592cc573cf4e4176b1 0.8364 1.19562 0.07162 9.7671
## gauss:c5f228477d0e8545684 0.8900 1.12353 0.07125 11.1186
## gauss:c6a6cbbc85ee0c60d11 2.6308 0.38011 0.84362 8.2044
## gauss:c70cca3a3293cb3ad8e 5.1479 0.19425 1.11671 23.7314
## gauss:c711008dd46b67172a3 0.8073 1.23869 0.07167 9.0937
## gauss:c75e22739857a7f14ff 3.3411 0.29930 1.36330 8.1884
## gauss:c773113266aba52b58b 0.6654 1.50276 0.07016 6.3113
## gauss:c78f84b962bffbef358 0.2816 3.55093 0.04772 1.6621
## gauss:c8e946c0969b02afb5b 0.7453 1.34173 0.07138 7.7824
## gauss:c8eb92088b0ecf40348 0.8415 1.18842 0.07160 9.8884
## gauss:c92a2354dd4f9e682c1 0.8253 1.21167 0.07165 9.5063
## gauss:c98a749292cd195b3fb 0.3053 3.27544 0.05010 1.8606
## gauss:c99cf98d03e06547153 0.7655 1.30636 0.07153 8.1917
## gauss:ca008f7c0ddf7c3919d 0.7106 1.40727 0.07097 7.1153
## gauss:ca2c9826af3f9294fbd 1.7133 0.58367 0.46039 6.3760
## gauss:ca38f7853f25d6bf84a 0.8988 1.11259 0.07115 11.3538
## gauss:caed8ad87436b2a80fd 6.7006 0.14924 2.63796 17.0200
## gauss:cbc41acfc4793c367b5 0.9233 1.08308 0.07084 12.0346
## gauss:cbcc167be42c3d98772 0.8005 1.24920 0.07166 8.9422
## gauss:cc16d7f0ab9f8c36561 5.6150 0.17809 1.19052 26.4827
## gauss:cce6c1dbd6f120f0994 0.9008 1.11012 0.31547 2.5722
## gauss:ccec2085e7795e09b22 4.0852 0.24479 1.25167 13.3332
## gauss:cd417aba2c9b49998e3 0.7497 1.33386 0.07142 7.8702
## gauss:cd508fd8122a5dd1b87 4.2689 0.23425 2.08705 8.7317
## gauss:cd7a8c5bfb4697a291c 17.8513 0.05602 2.46438 129.3105
## gauss:cd8c90426552c1e4cf6 0.6623 1.50984 0.07010 6.2581
## gauss:cdb4ac83dd91de0449f 5.4249 0.18434 2.50227 11.7610
## gauss:cdb717a2c28c59cac59 0.8643 1.15701 0.07147 10.4516
## gauss:cdef617cb5c0e33c673 0.5788 1.72761 0.06768 4.9504
## gauss:ce5f627da695c257baa 0.8595 1.16349 0.07150 10.3310
## gauss:cef24a2863ab703de8d 0.8696 1.14997 0.07143 10.5858
## gauss:cf393be5e8ac0ef240b 0.6623 1.50984 0.07010 6.2581
## gauss:cf52e8fdca10c3061c3 0.4455 2.24470 0.06117 3.2446
## gauss:cfad5e0ec91edaf37d1 0.4680 2.13683 0.06251 3.5035
## gauss:cfbcc1810da43caf7b8 0.9034 1.10689 0.07110 11.4797
## gauss:cfbe590772260695aa0 0.6756 1.48010 0.07037 6.4865
## gauss:cfd979d464446db2ce4 1.7011 0.58786 0.45761 6.3235
## gauss:cfefcb7c2ebb6cbd7f1 0.6523 1.53303 0.06987 6.0902
## gauss:d03a464081188a5765d 2.4829 0.40276 0.62731 9.8272
## gauss:d056e40555fcfcb2c61 0.3402 2.93960 0.05328 2.1722
## gauss:d05a2c4117ac78969b8 0.9191 1.08806 0.07090 11.9145
## gauss:d063eebc542ae8d7e80 0.5733 1.74422 0.06748 4.8711
## gauss:d0728cdb690d6a4530b 2.0482 0.48824 0.53557 7.8327
## gauss:d0a4bbc2557a968ed10 0.6698 1.49304 0.07025 6.3854
## gauss:d0c7b8353a305221dff 0.4626 2.16149 0.06220 3.4412
## gauss:d0f1cbce56a3f4b842c 0.4062 2.46178 0.05852 2.8194
## gauss:d129899b8403ad85f33 0.4993 2.00292 0.06421 3.8818
## gauss:d188eca4d8d31f6f380 0.4650 2.15037 0.06234 3.4687
## gauss:d1ba489c1349b4c9650 1.5411 0.64891 0.42101 5.6408
## gauss:d1de6d551ef51f42190 0.7936 1.26014 0.07165 8.7890
## gauss:d1ed6b2d821a723c5bd 2.2978 0.43520 0.58907 8.9630
## gauss:d25298f62486527441f 0.4276 2.33883 0.06000 3.0468
## gauss:d273c6c9021d1395979 0.6703 1.49177 0.07027 6.3951
## gauss:d275ca2820adebd8d2c 7.0427 0.14199 2.01507 24.6140
## gauss:d37229491a5cb520755 0.9034 1.10689 0.07110 11.4797
## gauss:d376d7664161d5e2824 0.9794 1.02104 0.28279 3.3920
## gauss:d3a861ce7dd7cf7fb24 0.5799 1.72445 0.06772 4.9659
## gauss:d3e3a0653a59527ef92 0.4783 2.09063 0.06310 3.6262
## gauss:d419b9b0b527b75db0a 0.8073 1.23869 0.07167 9.0937
## gauss:d43208104d37f413bd7 0.9424 1.06114 0.07054 12.5901
## gauss:d461c943d3d6bf650d7 0.5515 1.81326 0.06663 4.5649
## gauss:d4655bf71c36038ddb7 0.9753 1.02536 0.06993 13.6015
## gauss:d4898e889c0bf66c6d3 0.5241 1.90818 0.06542 4.1978
## gauss:d4d497b86545ce52bb4 3.2616 0.30660 1.44115 7.3814
## gauss:d5d26c4b3677a60b270 0.5418 1.84569 0.06622 4.4332
## gauss:d5db87174f537607908 0.3983 2.51090 0.05795 2.7369
## gauss:d6221547c32fff7039b 4.0594 0.24634 1.24349 13.2520
## gauss:d6261087879f89add9f 0.4600 2.17414 0.06204 3.4100
## gauss:d65f6a001384cd5d840 0.5100 1.96092 0.06475 4.0164
## gauss:d7031818302a8758082 1.2423 0.80497 0.34982 4.4115
## gauss:d72ececc6f8dcffdb5b 0.5466 1.82953 0.06642 4.4981
## gauss:d734b0db77bf856b2b4 0.3219 3.10681 0.05159 2.0083
## gauss:d73be4ee11707559112 0.9674 1.03366 0.07008 13.3543
## gauss:d82ef70bf13e4d1dd2d 0.1474 6.78385 0.03039 0.7150
## gauss:d8a07324fa2a41e4e8d 0.8587 1.16455 0.07151 10.3111
## gauss:d8e3e00cbd944dc148b 0.5241 1.90818 0.06542 4.1978
## gauss:d9b8d2650131d69d5b3 0.9948 1.00521 0.06951 14.2379
## gauss:da2513029dfa8d1f7ae 1.3367 0.74809 0.37272 4.7941
## gauss:dac95b5c662cf9f6986 0.9714 1.02942 0.07001 13.4798
## gauss:dacad4750cd63c35382 0.8087 1.23660 0.07167 9.1244
## gauss:daf93c9d0e24f73c23c 0.5355 1.86727 0.06595 4.3490
## gauss:db341e1ab88fed8662b 6.7632 0.14786 1.36470 33.5176
## gauss:dba3982d849aee77d28 0.3321 3.01092 0.05260 2.0970
## gauss:dbc229e9009ee4489ec 0.6371 1.56959 0.06949 5.8412
## gauss:dbcfd73218d102977db 0.9311 1.07401 0.07072 12.2587
## gauss:dc00ca9f83f475a93ec 0.9689 1.03209 0.07006 13.4005
## gauss:dcb277e59e1b0295d59 0.9347 1.06984 0.07066 12.3642
## gauss:dd250bbb74290bca99e 6.1774 0.16188 1.79805 21.2234
## gauss:dd263e9ff711610e0e5 0.6010 1.66401 0.06844 5.2772
## gauss:dd2fd45b4522155b75f 0.5135 1.94758 0.06492 4.0609
## gauss:de4809d45abd6e92a8c 0.9693 1.03171 0.07005 13.4116
## gauss:dea3ee52e22bf012844 0.9656 1.03568 0.07012 13.2952
## gauss:df5122bd4f634e249b4 0.4375 2.28546 0.06067 3.1557
## gauss:dfa367380a4b452e8b5 1.3117 0.76236 0.36757 4.6809
## gauss:e04a6b0d73d9639a12e 0.8735 1.14485 0.07140 10.6852
## gauss:e0929935739519b965e 0.6514 1.53512 0.06985 6.0755
## gauss:e0b04b122dd17e8f1e2 6.9796 0.14327 1.99935 24.3653
## gauss:e14f93dd5956c52f02b 0.5060 1.97625 0.06456 3.9662
## gauss:e1c0b3eb49b369b77b5 0.9005 1.11043 0.07113 11.4010
## gauss:e1f8b07ef3b990a42d5 0.4187 2.38853 0.05941 2.9502
## gauss:e1fd653a5dc20735804 0.8172 1.22364 0.07166 9.3193
## gauss:e23deaadb9525ceca66 0.6724 1.48731 0.07031 6.4299
## gauss:e253daf4a52dc88680a 0.9371 1.06714 0.07063 12.4336
## gauss:e28fd4aad8b18584bea 0.9371 1.06714 0.07063 12.4336
## gauss:e3b08bf7d20113bac89 0.2671 3.74374 0.04616 1.5456
## gauss:e42bdca02ee5b47ad3c 1.9206 0.52067 0.50707 7.2745
## gauss:e4d3c4bbef63d3a35ef 0.9512 1.05129 0.07039 12.8547
## gauss:e4e2632358ac06afb10 10.7733 0.09282 1.86603 62.1984
## gauss:e4f2602edf7beefb1c0 6.8759 0.14544 1.97126 23.9834
## gauss:e51bb0323e48291749f 0.6791 1.47254 0.07044 6.5471
## gauss:e57945cbd6128d7feba 0.9141 1.09395 0.07096 11.7756
## gauss:e5e1052262a5796375d 2.2073 0.45304 0.56924 8.5592
## gauss:e62929a2f47729d6e7c 4.3351 0.23068 1.31818 14.2568
## gauss:e63aae13ec425bd1f60 3.7314 0.26800 1.35567 10.2704
## gauss:e676a362ffe81ff7f38 0.9371 1.06714 0.07063 12.4336
## gauss:e6c91b74164e2ca3c88 0.8722 1.14648 0.07141 10.6534
## gauss:e6e0a63dc7ed2b5269f 0.4247 2.35462 0.05982 3.0151
## gauss:e72763cdf316cb523ed 0.9300 1.07523 0.07074 12.2281
## gauss:e75a6cce0980aeb3bf4 0.8141 1.22832 0.07167 9.2479
## gauss:e76c56fa8fd6a0be61d 0.6868 1.45595 0.07059 6.6833
## gauss:e7acf2b5549e21e3401 0.8504 1.17585 0.07156 10.1070
## gauss:e7c24f00d9c33e1e53d 0.7726 1.29433 0.23115 2.5823
## gauss:e827fc524f93f65c15f 0.6944 1.44010 0.07071 6.8188
## gauss:e83a18ad8cc134d398c 0.9517 1.05077 0.07038 12.8690
## gauss:e8e0915f327a78b95f2 0.7782 1.28508 0.07160 8.4572
## gauss:e8e2a8672e1e9b345ea 1.4766 0.67723 0.40541 5.3782
## gauss:e8f89494413e3eb8d2c 0.6890 1.45138 0.07062 6.7220
## gauss:e963587905607510556 0.5634 1.77507 0.06710 4.7300
## gauss:e9b02bba768806f4a5b 0.8808 1.13529 0.07134 10.8758
## gauss:e9c1d2ea7643e3517cf 0.5487 1.82249 0.06651 4.5266
## gauss:ea150000fbd2ee9d7ac 0.8087 1.23660 0.07167 9.1244
## gauss:ea539bc48d0295d58a1 0.9341 1.07053 0.07067 12.3468
## gauss:ea70eb599fe8ed248a0 1.0561 0.94691 0.36151 3.0850
## gauss:ea8a0ff36efa28affc0 0.5083 1.96749 0.15657 1.6500
## gauss:ea8aeb35fa25cc64fda 0.1459 6.85571 0.03026 0.7032
## gauss:eaf732c5974880daa36 0.8666 1.15399 0.07146 10.5089
## gauss:eb2daa5f3870b957f3c 2.7261 0.36683 0.67749 10.9689
## gauss:ebcb916128d64aebb6a 0.9792 1.02122 0.06985 13.7280
## gauss:ebd728c0b6c11cd37af 0.9746 1.02605 0.06994 13.5807
## gauss:ec018f8f0e065a7d243 1.7256 0.57952 0.57541 5.1747
## gauss:ec6f907b13c31fa3b49 0.3638 2.74911 0.05528 2.3936
## gauss:ecb53d3bcd8d8521bae 0.6620 1.51064 0.07009 6.2524
## gauss:ecc3a31bcc6fc956853 0.4472 2.23605 0.06127 3.2645
## gauss:eda5748bc334769a711 0.3684 2.71421 0.05569 2.4376
## gauss:edfc02fe922d947445a 0.6233 1.60443 0.06911 5.6208
## gauss:ee0c589b771ffebe11b 0.7164 1.39583 0.07105 7.2239
## gauss:ee2371f7d4fc4909159 0.9753 1.02536 0.06993 13.6015
## gauss:ee774d49ddfca8a111d 0.7303 1.36927 0.07122 7.4886
## gauss:eec71a0e929e116a1a6 0.9075 1.10198 0.07105 11.5902
## gauss:eed900fed151c33c1c0 0.8703 1.14909 0.07143 10.6027
## gauss:eeeb9bc68f58977049b 0.7027 1.42299 0.07085 6.9704
## gauss:ef0bc764db3884c25e5 0.9063 1.10338 0.07106 11.5586
## gauss:ef7f33654126258ddd8 0.3321 3.01092 0.05260 2.0970
## gauss:efa6d5bc489cc6f7fc6 0.8985 1.11302 0.07116 11.3444
## gauss:f019ac52c8028701d12 3.1763 0.31483 0.76632 13.1654
## gauss:f081ac52232781af3b5 5.5256 0.18098 1.63279 18.6995
## gauss:f0ed2263326e0093c72 0.6596 1.51610 0.07004 6.2119
## gauss:f1083e38dbaef75db08 0.6611 1.51260 0.07006 6.2383
## gauss:f11cc76d3846d562a4c 0.9279 1.07769 0.07077 12.1667
## gauss:f147de34da4a7c35713 0.7584 1.31861 0.07148 8.0460
## gauss:f198e2b5d5407cbb649 0.3728 2.68243 0.05600 2.4818
## gauss:f19d5c48a4972b00c64 3.5201 0.28408 0.83198 14.8935
## gauss:f1d88eb1427aca3fff0 3.5143 0.28456 0.83101 14.8613
## gauss:f2065e15d20bb933b1c 1.9143 0.52238 0.63422 5.7780
## gauss:f25d59899d94e6533d9 0.9512 1.05129 0.07039 12.8547
## gauss:f285d24905d4609da60 0.7401 1.35113 0.07133 7.6798
## gauss:f2cda4b4cd7c28a4ec9 0.9769 1.02366 0.06990 13.6532
## gauss:f307d6f97ac7aaf3d49 0.6447 1.55107 0.06968 5.9648
## gauss:f33762d178d8f40ffd0 7.4974 0.13338 1.46653 38.3295
## gauss:f37e0b2dbeb8e3397e9 0.9300 1.07523 0.07074 12.2281
## gauss:f380aceb3492ee5b4b8 0.5788 1.72761 0.06768 4.9504
## gauss:f38226c7aa1ffc30e89 0.9927 1.00733 0.06956 14.1687
## gauss:f3df6dc44a594f98796 0.8415 1.18842 0.07160 9.8884
## gauss:f49487a02683296ef9e 0.8581 1.16540 0.07152 10.2955
## gauss:f4c14052e921f4cb69a 0.7169 1.39486 0.07105 7.2335
## gauss:f4c2cf7d271ee6304a6 0.6074 1.64641 0.06864 5.3745
## gauss:f501712d105a17ba934 0.9446 1.05863 0.07050 12.6565
## gauss:f514956d63aaf24025b 0.5632 1.77543 0.06710 4.7282
## gauss:f58e105521a89466d0c 18.2668 0.05474 2.48685 134.1758
## gauss:f5a0be890e32f066acc 0.7059 1.41657 0.07090 7.0288
## gauss:f5bf8065c1361fb32fe 9.9772 0.10023 2.72011 36.5955
## gauss:f66f3888cb6359668dc 0.4871 2.05289 0.06358 3.7323
## gauss:f682c3b1ba990a3f6ba 6.2483 0.16004 1.81611 21.4970
## gauss:f6c2f24c639ce422161 0.6654 1.50276 0.07016 6.3113
## gauss:f6e38a7ab904f329f0a 0.5980 1.67224 0.06834 5.2327
## gauss:f7117ecf7d69026e597 0.6898 1.44967 0.07064 6.7365
## gauss:f7a518a2958dbbba26a 0.8524 1.17320 0.07155 10.1541
## gauss:f84e0610a4ac8a006ae 0.4811 2.07843 0.06325 3.6598
## gauss:f8b261902dd1a285000 3.9815 0.25116 0.91677 17.2916
## gauss:f98372dd73093dd4c3c 0.9978 1.00217 0.06944 14.3387
## gauss:f9a403b622f30f06e94 0.7270 1.37559 0.07118 7.4243
## gauss:fa81a98a8237a63a775 3.5564 0.28119 1.29513 9.7656
## gauss:faf8649dc93e8befb43 0.4164 2.40180 0.05924 2.9263
## gauss:fb0634489492c59cdad 1.7797 0.56189 0.47636 6.6491
## gauss:fb87cb92ac70cff85d4 0.3241 3.08509 0.05183 2.0273
## gauss:fb8d53ba7a380f93d27 0.9459 1.05721 0.07048 12.6944
## gauss:fbd244019b251ca29ec 0.6724 1.48731 0.07031 6.4299
## gauss:fbfaf8b81a7b1ae3efa 0.4559 2.19364 0.06179 3.3629
## gauss:fc3c98bf241e849fbc2 2.3047 0.43389 0.59010 9.0015
## gauss:fc51a5a18c5d10153d6 1.9459 0.51389 0.73834 5.1286
## gauss:fcbcf5f0eaa4bbfa418 5.0085 0.19966 1.09332 22.9438
## gauss:fd9ef2de3315beb20c4 0.9400 1.06387 0.07058 12.5184
## gauss:fded5a3df862d4ca956 3.9168 0.25531 0.90488 16.9543
## gauss:fe1ab48d6a38b9974d6 6.8379 0.14624 1.96618 23.7807
## gauss:fe92cf38a3c38bff297 0.2340 4.27417 0.04237 1.2919
## gauss:ff115bb1fae067a7d81 0.7536 1.32702 0.22572 2.5158
## gauss:ff3677387f825f7668e 0.9693 1.03171 0.07005 13.4116
## gauss:ff911d34896ad240f9d 0.7226 1.38380 0.07113 7.3416
## gauss:ffdaa0188fab7b73bbb 1.1065 0.90377 0.38280 3.1982
## gauss:ffec437a77a4740887f 0.9191 1.08806 0.07090 11.9145
## gauss:ffedb440851160fab52 0.9131 1.09513 0.07098 11.7478
##
## Iterations: 6 outer, 20 Newton-Raphson
## Variance of random effect= 1.853021
## Degrees of freedom for terms= 0.7 401.1
## Concordance= 0.877 (se = 0.877 )
## Likelihood ratio test= 3240 on 401.9 df, p=<2e-16#cox.zph(m3)#Possibly, a log-normal or log-logistic AFT model would fit better than Cox.There was evidence of proportional hazards.
library("mstate")
d_match_surv %>%
tidyr::pivot_wider(names_from=dup,values_from=c("motivodeegreso_mod_imp","diff_bet_treat","dias_treat_imp_sin_na","evaluacindelprocesoteraputico","abandono_temprano_rec"))
#.s-variables are the corresponding status variables (1 for an event,
tmat <- transMat(x = list(c(2, 3, 5, 6), c(4, 5, 6), c(4, 5, 6), c(5, 6),
c(), c()), names = c("Tx", "Rec", "AE", "Rec+AE", "Rel", "Death"))Session Info
Sys.getenv("R_LIBS_USER")## [1] "C:/Users/CISS Fondecyt/OneDrive/Documentos/R/win-library/4.0"rstudioapi::getSourceEditorContext()## Document Context:
## - id: 'D1198717'
## - path: 'G:/Mi unidad/Alvacast/SISTRAT 2019 (github)/SUD_CL/Matching_Process_NOV.Rmd'
## - contents: <3307 rows>
## Document Selection:
## - [3268, 18] -- [3268, 18]: ''sessionInfo()## R version 4.0.2 (2020-06-22)
## Platform: x86_64-w64-mingw32/x64 (64-bit)
## Running under: Windows 10 x64 (build 18363)
##
## Matrix products: default
##
## locale:
## [1] LC_COLLATE=Spanish_Chile.1252 LC_CTYPE=Spanish_Chile.1252
## [3] LC_MONETARY=Spanish_Chile.1252 LC_NUMERIC=C
## [5] LC_TIME=Spanish_Chile.1252
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] frailtySurv_1.3.6 lubridate_1.7.9 Amelia_1.7.6
## [4] Rcpp_1.0.5 polycor_0.7-10 compareGroups_4.4.5
## [7] DiagrammeR_1.0.6.1.9000 gurobi_9.1-0 radiant.update_1.4.1
## [10] cobalt_4.2.3 sensitivityfull_1.5.6 sensitivity2x2xk_1.01
## [13] MatchIt_3.0.2 tableone_0.12.0 stargazer_5.2.2
## [16] reshape2_1.4.4 exactRankTests_0.8-31 gridExtra_2.3
## [19] foreign_0.8-80 glpkAPI_1.3.2 designmatch_0.3.1
## [22] Rglpk_0.6-4 slam_0.1-47 MASS_7.3-51.6
## [25] survMisc_0.5.5 ggfortify_0.4.10 rateratio.test_1.0-2
## [28] survminer_0.4.8 ggpubr_0.4.0 epiR_1.0-15
## [31] forcats_0.5.0 purrr_0.3.4 readr_1.3.1
## [34] tibble_3.0.3 tidyverse_1.3.0 treemapify_2.5.3
## [37] ggiraph_0.7.0 chilemapas_0.2 sf_0.9-3
## [40] finalfit_1.0.1 lsmeans_2.30-0 emmeans_1.4.8
## [43] choroplethrAdmin1_1.1.1 choroplethrMaps_1.0.1 choroplethr_3.6.3
## [46] acs_2.1.4 XML_3.99-0.3 RColorBrewer_1.1-2
## [49] panelr_0.7.3 lme4_1.1-23 Matrix_1.2-18
## [52] dplyr_1.0.1 data.table_1.13.0 codebook_0.9.2
## [55] devtools_2.3.0 usethis_1.6.1 sqldf_0.4-11
## [58] RSQLite_2.2.0 gsubfn_0.7 proto_1.0.0
## [61] broom_0.7.0 zoo_1.8-8 altair_4.0.1
## [64] rbokeh_0.5.1 janitor_2.0.1 plotly_4.9.2.1
## [67] kableExtra_1.1.0 Hmisc_4.4-0 Formula_1.2-3
## [70] survival_3.1-12 lattice_0.20-41 ggplot2_3.3.2
## [73] stringr_1.4.0 stringi_1.4.6 tidyr_1.1.1
## [76] knitr_1.29 matrixStats_0.56.0 boot_1.3-25
##
## loaded via a namespace (and not attached):
## [1] class_7.3-17 ps_1.3.3 rprojroot_1.3-2
## [4] crayon_1.3.4 V8_3.1.0 nlme_3.1-148
## [7] backports_1.1.7 reprex_0.3.0 ggcorrplot_0.1.3
## [10] rlang_0.4.7 readxl_1.3.1 performance_0.4.8
## [13] nloptr_1.2.2.2 callr_3.4.3 flextable_0.5.10
## [16] rjson_0.2.20 ggmap_3.0.0 bit64_0.9-7
## [19] glue_1.4.1 sjPlot_2.8.4 parallel_4.0.2
## [22] processx_3.4.3 classInt_0.4-3 tcltk_4.0.2
## [25] haven_2.3.1 tidyselect_1.1.0 km.ci_0.5-2
## [28] rio_0.5.16 nleqslv_3.3.2 sjmisc_2.8.5
## [31] chron_2.3-55 xtable_1.8-4 magrittr_1.5
## [34] evaluate_0.14 gdtools_0.2.2 RgoogleMaps_1.4.5.3
## [37] cli_2.0.2 rstudioapi_0.11 sp_1.4-2
## [40] rpart_4.1-15 jtools_2.0.5 sjlabelled_1.1.6
## [43] RJSONIO_1.3-1.4 maps_3.3.0 gistr_0.5.0
## [46] xfun_0.16 parameters_0.8.2 pkgbuild_1.1.0
## [49] cluster_2.1.0 ggfittext_0.9.0 png_0.1-7
## [52] withr_2.2.0 bitops_1.0-6 plyr_1.8.6
## [55] cellranger_1.1.0 e1071_1.7-3 survey_4.0
## [58] coda_0.19-3 pillar_1.4.6 multcomp_1.4-13
## [61] fs_1.5.0 vctrs_0.3.2 ellipsis_0.3.1
## [64] generics_0.0.2 rgdal_1.5-8 tools_4.0.2
## [67] munsell_0.5.0 compiler_4.0.2 pkgload_1.1.0
## [70] abind_1.4-5 tigris_0.9.4 sessioninfo_1.1.1
## [73] visNetwork_2.0.9 jsonlite_1.7.0 WDI_2.6.0
## [76] scales_1.1.1 carData_3.0-4 estimability_1.3
## [79] lazyeval_0.2.2 car_3.0-8 latticeExtra_0.6-29
## [82] reticulate_1.16 effectsize_0.3.2 checkmate_2.0.0
## [85] rmarkdown_2.5 openxlsx_4.1.5 sandwich_2.5-1
## [88] statmod_1.4.34 webshot_0.5.2 pander_0.6.3
## [91] numDeriv_2016.8-1.1 yaml_2.2.1 systemfonts_0.2.3
## [94] htmltools_0.5.0 memoise_1.1.0 viridisLite_0.3.0
## [97] jsonvalidate_1.1.0 digest_0.6.25 assertthat_0.2.1
## [100] rappdirs_0.3.1 repr_1.1.0 bayestestR_0.7.2
## [103] BiasedUrn_1.07 KMsurv_0.1-5 units_0.6-6
## [106] remotes_2.2.0 blob_1.2.1 splines_4.0.2
## [109] labeling_0.3 hms_0.5.3 rmapshaper_0.4.4
## [112] modelr_0.1.8 colorspace_1.4-1 base64enc_0.1-3
## [115] nnet_7.3-14 mvtnorm_1.1-1 fansi_0.4.1
## [118] truncnorm_1.0-8 R6_2.4.1 grid_4.0.2
## [121] crul_0.9.0 lifecycle_0.2.0 acepack_1.4.1
## [124] labelled_2.5.0 zip_2.1.1 writexl_1.3
## [127] curl_4.3 geojsonlint_0.4.0 ggsignif_0.6.0
## [130] pryr_0.1.4 minqa_1.2.4 testthat_2.3.2
## [133] snakecase_0.11.0 desc_1.2.0 TH.data_1.0-10
## [136] htmlwidgets_1.5.1 officer_0.3.13 crosstalk_1.1.0.1
## [139] rvest_0.3.6 insight_0.9.0 htmlTable_2.0.1
## [142] codetools_0.2-16 prettyunits_1.1.1 dbplyr_1.4.4
## [145] vegawidget_0.3.1 gtable_0.3.0 DBI_1.1.0
## [148] httr_1.4.2 highr_0.8 KernSmooth_2.23-17
## [151] farver_2.0.3 uuid_0.1-4 hexbin_1.28.1
## [154] mice_3.11.0 xml2_1.3.2 ggeffects_0.15.1
## [157] bit_1.1-15.2 sjstats_0.18.0 jpeg_0.1-8.1
## [160] pkgconfig_2.0.3 maptools_1.0-1 rstatix_0.6.0
## [163] mitools_2.4 HardyWeinberg_1.6.6 Rsolnp_1.16
## [166] httpcode_0.3.0